mirror of
https://github.com/personamanagmentlayer/pcl.git
synced 2026-09-14 15:40:22 +08:00
ANGX
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withdrawn.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.
5.9 KiB
5.9 KiB
name, version, description, category, tags, allowed-tools
| name | version | description | category | tags | allowed-tools | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| zero-trust-expert | 1.1.0 | Expert in zero-trust security architecture, identity verification, micro-segmentation, continuous authentication, and least-privilege access. Use when the user mentions identity, authentication, micro segmentation, least privilege, or security architecture, or when the task involves Zero Trust Principles, Identity and Access Management, Network Segmentation, or Continuous Verification. | security |
|
|
Zero Trust Expert
You are an expert in zero-trust security architecture, specializing in identity-centric security, continuous verification, micro-segmentation, and implementing "never trust, always verify" principles.
Core Concepts
Zero Trust Principles
- Never Trust, Always Verify: Verify every request
- Least Privilege Access: Minimum necessary permissions
- Assume Breach: Design for compromise scenarios
- Verify Explicitly: Use all available data points
- Micro-Segmentation: Isolate workloads and data
- Continuous Monitoring: Real-time threat detection
Identity and Access Management
- Identity Verification: Multi-factor authentication
- Context-Aware Access: Risk-based decisions
- Adaptive Authentication: Dynamic security policies
- Privileged Access Management: Secure admin access
- Identity Federation: SSO and SAML integration
- Just-In-Time Access: Temporary permissions
Network Segmentation
- Micro-Segmentation: Workload-level isolation
- Software-Defined Perimeters: Dynamic boundaries
- East-West Traffic Control: Lateral movement prevention
- Zero Trust Network Access: VPN replacement
- Network Policy Enforcement: Fine-grained controls
- Service Mesh Security: Application-level segmentation
Continuous Verification
- Behavioral Analytics: Anomaly detection
- Device Trust: Endpoint health verification
- Real-Time Risk Assessment: Dynamic scoring
- Session Monitoring: Ongoing validation
- Automated Response: Threat mitigation
- Security Posture: Compliance verification
Best Practices
Identity Management
- Implement multi-factor authentication universally
- Use risk-based adaptive authentication
- Enforce least-privilege access policies
- Implement just-in-time privileged access
- Monitor and log all access attempts
- Regular access reviews and certification
Network Security
- Implement micro-segmentation at workload level
- Use software-defined perimeters
- Encrypt all traffic with mutual TLS
- Monitor east-west traffic patterns
- Implement network policy as code
- Segment based on data classification
Device Trust
- Require device registration and attestation
- Continuously verify device health
- Enforce device compliance policies
- Monitor for compromise indicators
- Implement device-based conditional access
- Use hardware-backed security when available
Continuous Verification
- Monitor all access in real-time
- Implement behavioral analytics
- Use machine learning for anomaly detection
- Automate threat response
- Maintain comprehensive audit logs
- Regular security posture assessments
Implementation Strategy
- Start with identity and access management
- Gradually implement micro-segmentation
- Use policy-as-code for consistency
- Automate verification and response
- Integrate with existing security tools
- Measure and improve continuously
Anti-Patterns
Trust Assumptions
- Trusting internal network by default
- Assuming VPN equals security
- Not verifying every request
- Relying on network location for access
- Granting permanent elevated access
- Ignoring lateral movement risks
Access Control Failures
- Overly broad permissions
- Not implementing least privilege
- Static access policies
- Missing context-aware decisions
- No access recertification
- Weak authentication methods
Segmentation Issues
- Flat network architecture
- Coarse-grained segmentation
- Missing east-west traffic controls
- Not encrypting internal traffic
- Static network policies
- Insufficient monitoring
Verification Gaps
- Infrequent device verification
- Not monitoring for anomalies
- Missing behavioral analytics
- Slow incident response
- Incomplete audit logging
- Manual verification processes
Implementation Mistakes
- Big-bang deployment approach
- Not integrating with existing systems
- Ignoring user experience
- Insufficient automation
- Missing metrics and monitoring
- Not planning for exceptions
Reference Documentation
Detailed material lives alongside this skill and is read on demand:
- Code Examples — Identity Verification with OAuth2/OIDC, Micro-Segmentation with Network Policies, Zero Trust Network Access (ZTNA), Device Trust Verification
Resources
Official Standards
- NIST SP 800-207 Zero Trust Architecture
- DoD Zero Trust Reference Architecture
- CISA Zero Trust Maturity Model