mirror of
https://github.com/personamanagmentlayer/pcl.git
synced 2026-09-14 15:40:22 +08:00
4e07a6a874
* chore(stdlib): add conformance tooling for the skills library
The library had no gate that could express what a valid skill is, so
malformed frontmatter, over-budget files and credential literals went
unnoticed. These scripts define and enforce that contract.
- validate-skills.py: extend with Agent Skills v1.0 conformance -
naming rules and directory agreement, an explicit activation trigger
in the description, canonical layout, the 500-line SKILL.md budget,
relative-link integrity, and two security rules (no unrestricted
Bash(*) grant, no credential literals). Structural checks now read a
skill as a whole so material moved into references/ still counts.
- split-skill-references.py: move the heaviest sections of an oversized
SKILL.md into references/. Verifies line by line that every source
line lands in exactly one output and refuses to write otherwise.
- generate-skill-inventory.py: derive SKILLS_INVENTORY.md and
DIRECTORY_STRUCTURE.md from the tree so they cannot drift.
- generate-skill-catalog.py: index the canonical layout only, count
references/ toward a skill's size, and stop truncating descriptions
at 200 characters - the catalog is the discovery surface and must
carry the activation trigger.
- .gitignore: Python bytecode from these scripts, and local .pcl state.
Reviewed-by: Security Analyst, Compiler Engineer, DevX Engineer
* fix(stdlib): bring all 174 skills to Agent Skills v1.0 conformance
No skill in the library was conformant. 41 of 175 failed the existing
validator outright, and none satisfied the spec. This pass fixes the
tree and records the result. See stdlib/CHANGELOG.md for the per-skill
versioning and migration notes.
BREAKING CHANGE: one skill removed, five moved, seven with a capability
withdrawn. Library version 2.0.0 -> 3.0.0.
Structure
- Convert 71 skills stored as flat files to <category>/<name>/SKILL.md,
the layout the spec requires and the only one able to carry companion
resources.
- Rename 5 directories that disagreed with their declared name:, so
resolution by path and by name stop giving different answers. The
repository docs already referenced the corrected paths.
- Merge the duplicate legal-technology skills into legaltech-expert and
delete legal-tech-expert, carrying over everything the survivor
lacked.
Metadata
- Repair 20 unparseable frontmatters: an H1 preceded the --- block and
the key was skill_id: instead of name:, so any parser reading
frontmatter at offset 0 saw no metadata at all. The objectives,
prerequisites and outcome they carried become real body sections.
- Add the missing version: to 21 skills, fold keywords into tags, move
expertise_level under metadata, and align 10 category: values with
their directory.
Discoverability
- Give all 174 descriptions an explicit "Use when ..." trigger, built
from each skill's own tags and section headings. 152 previously said
only what the skill was about, leaving an agent nothing to match on.
Progressive disclosure
- Split 127 oversized skills, moving bulk material into references/ read
on demand and leaving an index behind. A SKILL.md now averages 277
lines instead of 644 and none exceeds 500. Verified lossless line by
line against the previous revision.
Security
- Withdraw the unrestricted Bash(*) grant from 7 skills; none of the six
non-financial ones contained a single shell command. finance-expert
documents code that charges cards and reads bank accounts, so it now
grants no shell at all.
- Remove credential literals: Stripe keys, two JWT signing keys, an
Express session secret, a Redis password and WiFi credentials, all
inlined in examples. They load from the environment now.
- finance-expert: idempotency keys were documented but absent, so a
retry double-charged; webhook signature failures were not caught, so a
forged event raised uncaught instead of being rejected;
int(amount * 100) truncated fractions of a cent. All fixed, plus a
money-movement guardrails section.
- trading-expert: place_order routed without any pre-trade risk check
although a RiskManager sat unused in the next section. Risk validation
now runs before routing and raises rather than returning a boolean a
caller can ignore; live routing is opt-in.
- Correct an Ansible Vault example that showed plaintext under an
"encrypted" label.
Also fixes 8 broken documentation links and a prematurely closed code
fence in skill-creator-expert that leaked template content into prose.
Per the repository file-organization policy, four stale progress reports
(SKILLS_MANIFEST, COMPLETE_SKILLS_LIBRARY, COMPLETE_LIBRARY_MANIFEST,
PHASE_3_DATA_ANALYTICS) move out of stdlib/ into the gitignored
.roadmap/status/stdlib/; they claimed 31 of 100 skills complete. They
appear here as deletions because .roadmap/ is not tracked.
Reviewed-by: Security Analyst, Language Designer, DevX Engineer,
Documentation Specialist
* fix(skills): resolve standard library skills from their real layout
No stdlib skill was resolvable. SkillResolver looked for
`<stdlibDir>/<name>.md` with stdlibDir defaulting to `stdlib/skills`, a
directory that does not exist, and the path ignored the category level
the library actually uses. The two LSP providers had the same wrong
directory and scanned only one level deep, so neither completion nor
go-to-definition could see a skill either.
- skill-discovery.ts: enumerate skill entry points across the shapes in
use - a flat `<name>.md`, `<name>/SKILL.md`, and
`<category>/<name>/SKILL.md` - while skipping references/, scripts/
and assets/, which hold supporting material rather than entry points.
- skill-resolver.ts: point stdlibDir at `stdlib`, and look the name up
as a directory under any category as well as the two legacy shapes, so
existing custom stdlib directories keep working. The name is used as a
single path segment and rejected if it contains a separator or
traversal, so a reference cannot escape the stdlib root.
- Rewire both LSP providers onto the shared discovery helper.
Tests: 13 new cases covering the layouts, ordering, the references/
exclusion, path-traversal rejection, and an integration test that
resolves real shipped skills by bare name.
Reviewed-by: Compiler Engineer, Runtime Architect, Security Analyst
* feat(stdlib): add 17 skills covering the library's largest gaps
Selection was driven by cross-referencing coverage against observed usage
rather than by intuition: Stack Overflow and GitHub Octoverse data for
which technologies matter, and install rankings on public agent-skill
registries for the shape of skills people actually use.
That comparison found a mismatch of form, not only of coverage. The
most-installed skills in the ecosystem are procedures - tdd, refactoring,
frontend design, browser automation - while all 174 existing skills were
domain knowledge shaped as <domain>-expert. The new workflows/ category
closes that gap and introduces the <activity>-workflow convention.
New category workflows/ (4)
- tdd-workflow, refactoring-workflow, debugging-workflow,
code-review-workflow. code-review-workflow complements rather than
replaces code-review-expert: procedure versus judgement. Merge them if
the split proves confusing in use.
Applied AI (3) - the largest coverage gap
- llm-engineering-expert, rag-expert, agent-engineering-expert.
The library referenced LLMs in tags but covered none of it: pgvector
appeared zero times across 174 skills, LangChain once, MCP twice
despite the repository shipping an MCP integration guide.
Capabilities (2)
- document-processing-expert (PDF, DOCX, XLSX, PPTX in one skill),
browser-automation-expert (a client against third-party sites,
distinct from playwright-expert which tests your own application).
Data (3)
- mysql-expert, the second most used database and previously absent
while rarer stores had skills; analytical-databases-expert;
stream-processing-expert.
Security (3)
- secrets-management-expert, supply-chain-security-expert (OWASP A03
2025), identity-access-expert (OWASP A01).
Interface and meta (2)
- accessibility-expert: design/ held only design-expert, which despite
its name covers software architecture, so WCAG had no home.
- skill-router: find and compose skills across 191, with a
disambiguation table for overlapping pairs.
Grouping by decision context rather than by technology keeps the growth
to 17 skills for roughly 50 topics. Five vector stores live inside
rag-expert; four document formats inside document-processing-expert.
Per-tool depth sits in references/, which the progressive-disclosure work
in 3.0.0 made cheap.
Four further gaps are better served by extending existing skills -
PyTorch and TensorFlow in ml-expert, OpenTelemetry in monitoring-expert,
Pulumi and Crossplane in terraform-expert - and are not in this change.
Library 3.0.0 -> 3.1.0, additive only. Adds the workflows label to the
inventory generator; catalogue, inventory, structure and CHANGELOG
regenerated.
Reviewed-by: Product Strategist, Security Analyst, DevX Engineer,
Documentation Specialist
* fix(test): create test directories with mkdtempSync
CodeQL flagged js/insecure-temporary-file (CWE-377) on both suites.
`join(tmpdir(), <predictable name>)` followed by mkdirSync creates a
world-readable directory at a guessable path, so another local user can
pre-create it or plant a symlink between the name being computed and the
directory being created.
mkdtempSync creates the directory atomically with a random suffix and
0700 permissions, which closes both the disclosure and the race.
One occurrence is new in this branch (skill-discovery); the other
pre-dates it in skill-resolver and is fixed in the same pass rather than
left as a known finding in a file this branch already touches.
12 KiB
12 KiB
name, version, description, category, tags, allowed-tools
| name | version | description | category | tags | allowed-tools | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| soc2-expert | 1.1.0 | Expert in SOC 2 compliance, trust service criteria, audit preparation, controls implementation, and security frameworks. Use when the user mentions compliance, audit, trust services, AICPA, controls, or security framework, or when the task involves Trust Service Criteria, SOC 2 Types, Security Common Criteria, or Control Implementation Framework. | security |
|
|
SOC 2 Expert
You are an expert in SOC 2 (System and Organization Controls 2) compliance, specializing in trust service criteria, audit preparation, controls implementation, and continuous monitoring.
Core Concepts
Trust Service Criteria (TSC)
- Security (Common Criteria): Protection against unauthorized access
- Availability: System availability for operation and use
- Processing Integrity: System processing is complete, valid, accurate, timely
- Confidentiality: Confidential information is protected
- Privacy: Personal information is collected, used, retained, disclosed appropriately
SOC 2 Types
- Type I: Design of controls at a specific point in time
- Type II: Operating effectiveness of controls over a period (usually 6-12 months)
- Report Structure: Description criteria, control objectives, auditor opinion
- Audit Period: Typically 6 months minimum for Type II
- Scope: Systems, services, and controls in scope
- Exceptions: Control failures and their impact
Security Common Criteria (CC)
- CC1: Control Environment
- CC2: Communication and Information
- CC3: Risk Assessment
- CC4: Monitoring Activities
- CC5: Control Activities
- CC6: Logical and Physical Access Controls
- CC7: System Operations
- CC8: Change Management
- CC9: Risk Mitigation
Code Examples
Control Implementation Framework
# soc2_controls.py - SOC 2 controls management system
from dataclasses import dataclass
from datetime import datetime
from enum import Enum
from typing import List, Optional
class ControlCategory(Enum):
CC1_CONTROL_ENVIRONMENT = "CC1"
CC2_COMMUNICATION = "CC2"
CC3_RISK_ASSESSMENT = "CC3"
CC4_MONITORING = "CC4"
CC5_CONTROL_ACTIVITIES = "CC5"
CC6_ACCESS_CONTROLS = "CC6"
CC7_SYSTEM_OPERATIONS = "CC7"
CC8_CHANGE_MANAGEMENT = "CC8"
CC9_RISK_MITIGATION = "CC9"
class ControlStatus(Enum):
DESIGNED = "designed"
IMPLEMENTED = "implemented"
OPERATING = "operating"
NOT_OPERATING = "not_operating"
REMEDIATED = "remediated"
@dataclass
class Control:
id: str
category: ControlCategory
description: str
control_owner: str
frequency: str # daily, weekly, monthly, quarterly, annual
evidence_required: List[str]
status: ControlStatus
last_tested: Optional[datetime] = None
exceptions: List[str] = None
def __post_init__(self):
if self.exceptions is None:
self.exceptions = []
class SOC2ControlsManager:
def __init__(self):
self.controls = {}
self.evidence = {}
self.exceptions = []
def add_control(self, control: Control):
"""Add a SOC 2 control to the framework."""
self.controls[control.id] = control
def test_control(self, control_id: str, test_results: dict):
"""Document control testing for audit."""
if control_id not in self.controls:
raise ValueError(f"Control {control_id} not found")
control = self.controls[control_id]
control.last_tested = datetime.now()
if test_results.get('passed'):
control.status = ControlStatus.OPERATING
else:
control.status = ControlStatus.NOT_OPERATING
self._log_exception(control, test_results.get('reason'))
self._store_evidence(control_id, test_results)
def collect_evidence(self, control_id: str, evidence: dict):
"""Collect audit evidence for controls."""
if control_id not in self.evidence:
self.evidence[control_id] = []
evidence['collected_at'] = datetime.now()
self.evidence[control_id].append(evidence)
def get_control_effectiveness(self, control_id: str) -> dict:
"""Calculate control operating effectiveness."""
if control_id not in self.controls:
return {'effective': False, 'reason': 'Control not found'}
control = self.controls[control_id]
evidence_items = self.evidence.get(control_id, [])
if control.status != ControlStatus.OPERATING:
return {'effective': False, 'reason': 'Control not operating'}
if not evidence_items:
return {'effective': False, 'reason': 'No evidence collected'}
# Calculate effectiveness based on testing frequency
required_tests = self._calculate_required_tests(control.frequency)
actual_tests = len(evidence_items)
effectiveness_rate = (actual_tests / required_tests) * 100 if required_tests > 0 else 0
return {
'effective': effectiveness_rate >= 95, # 95% threshold
'rate': effectiveness_rate,
'required_tests': required_tests,
'actual_tests': actual_tests
}
def generate_audit_report(self) -> dict:
"""Generate SOC 2 audit readiness report."""
report = {
'total_controls': len(self.controls),
'by_category': {},
'by_status': {},
'exceptions': len(self.exceptions),
'evidence_collected': sum(len(items) for items in self.evidence.values()),
'generated_at': datetime.now().isoformat()
}
# Count by category
for control in self.controls.values():
category = control.category.value
report['by_category'][category] = report['by_category'].get(category, 0) + 1
status = control.status.value
report['by_status'][status] = report['by_status'].get(status, 0) + 1
return report
def _log_exception(self, control: Control, reason: str):
"""Log control exceptions for audit report."""
exception = {
'control_id': control.id,
'category': control.category.value,
'description': control.description,
'reason': reason,
'logged_at': datetime.now(),
'owner': control.control_owner
}
self.exceptions.append(exception)
control.exceptions.append(exception)
def _calculate_required_tests(self, frequency: str) -> int:
"""Calculate required test samples based on frequency."""
# For 12-month audit period
frequency_map = {
'daily': 365,
'weekly': 52,
'monthly': 12,
'quarterly': 4,
'annual': 1
}
return frequency_map.get(frequency.lower(), 1)
def _store_evidence(self, control_id: str, evidence: dict):
"""Store evidence for audit trail."""
self.collect_evidence(control_id, evidence)
# Example usage
manager = SOC2ControlsManager()
# Add access control
access_control = Control(
id="CC6.1",
category=ControlCategory.CC6_ACCESS_CONTROLS,
description="Logical access is granted based on approved authorization",
control_owner="Security Team",
frequency="daily",
evidence_required=["Access logs", "Approval tickets", "User provisioning records"],
status=ControlStatus.IMPLEMENTED
)
manager.add_control(access_control)
# Test control
manager.test_control("CC6.1", {
'passed': True,
'tester': 'Audit Team',
'date': datetime.now(),
'evidence': 'Access logs reviewed'
})
Evidence Collection Automation
# evidence_collection.py - Automated evidence gathering
import boto3
import json
from datetime import datetime
class EvidenceCollector:
def __init__(self):
self.s3_client = boto3.client('s3')
self.evidence_bucket = 'soc2-evidence'
def collect_access_logs(self, start_date, end_date):
"""Collect access logs for CC6 controls."""
logs = self._query_cloudwatch_logs(start_date, end_date)
self._store_evidence('access_logs', logs)
return logs
def collect_change_tickets(self, start_date, end_date):
"""Collect change management tickets for CC8."""
tickets = self._query_jira('project = CHANGE', start_date, end_date)
self._store_evidence('change_tickets', tickets)
return tickets
def collect_security_scans(self):
"""Collect vulnerability scans for CC9."""
scans = self._get_latest_scans()
self._store_evidence('security_scans', scans)
return scans
def _store_evidence(self, evidence_type, data):
"""Store evidence in S3 for audit."""
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
key = f"{evidence_type}/{timestamp}.json"
self.s3_client.put_object(
Bucket=self.evidence_bucket,
Key=key,
Body=json.dumps(data, indent=2),
ServerSideEncryption='AES256'
)
def _query_cloudwatch_logs(self, start, end):
"""Query CloudWatch for access logs."""
# Implementation
return []
def _query_jira(self, jql, start, end):
"""Query Jira for tickets."""
# Implementation
return []
def _get_latest_scans(self):
"""Get latest security scans."""
# Implementation
return []
Best Practices
Audit Preparation
- Maintain continuous compliance year-round
- Automate evidence collection where possible
- Document all controls clearly
- Conduct regular internal audits
- Keep detailed audit trails
- Assign control owners and accountability
Control Design
- Map controls to TSC criteria
- Define clear control objectives
- Specify control frequency
- Document evidence requirements
- Design for automation
- Consider scalability
Evidence Management
- Collect evidence systematically
- Store evidence securely and immutably
- Organize by control and period
- Automate collection processes
- Maintain chain of custody
- Keep evidence for required retention period
Continuous Monitoring
- Monitor control effectiveness continuously
- Track exceptions and remediation
- Regular control testing
- Automated alerting for control failures
- Dashboard for compliance status
- Quarterly assessments
Remediation
- Document all exceptions
- Implement timely remediation
- Track remediation to closure
- Root cause analysis
- Prevent recurrence
- Update controls as needed
Anti-Patterns
Audit Failures
- Last-minute compliance efforts
- Missing or incomplete evidence
- Undocumented controls
- No control testing
- Ignoring exceptions
- Poor communication with auditors
Control Issues
- Poorly defined controls
- No assigned owners
- Infrequent testing
- Manual processes prone to error
- Controls not aligned to TSC
- Overlapping or redundant controls
Evidence Problems
- Missing evidence for audit period
- Evidence not retained
- Poor organization
- No automation
- Unverifiable evidence
- Inconsistent collection
Management Mistakes
- No executive buy-in
- Insufficient resources
- Treating SOC 2 as one-time project
- No continuous monitoring
- Ignoring control failures
- Poor exception management