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withdrawn.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.
10 KiB
10 KiB
name, version, description, category, tags, allowed-tools
| name | version | description | category | tags | allowed-tools | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ansible-expert | 1.1.0 | Expert-level Ansible for configuration management, automation, and infrastructure as code. Use when the user mentions automation, configuration management, infrastructure as code, playbooks, or roles, or when the task involves Ansible Architecture, Basic Inventory, YAML Inventory, or Dynamic Inventory. | devops |
|
|
Ansible Expert
Expert guidance for Ansible - configuration management, application deployment, and IT automation using declarative YAML playbooks.
Core Concepts
Ansible Architecture
- Control node (runs Ansible)
- Managed nodes (target systems)
- Inventory (hosts and groups)
- Playbooks (YAML automation scripts)
- Modules (units of work)
- Roles (reusable automation units)
- Plugins (extend functionality)
Key Features
- Agentless (SSH-based)
- Idempotent operations
- Declarative syntax
- Human-readable YAML
- Extensible with modules
- Push-based configuration
- Parallel execution
Use Cases
- Configuration management
- Application deployment
- Provisioning
- Continuous delivery
- Security automation
- Orchestration
Installation
# Using pip
pip install ansible
# Using apt (Ubuntu/Debian)
sudo apt update
sudo apt install ansible
# Using yum (RHEL/CentOS)
sudo yum install ansible
# Verify installation
ansible --version
Inventory
Basic Inventory (INI format)
# inventory/hosts
[webservers]
web1.example.com
web2.example.com ansible_host=192.168.1.10
[databases]
db1.example.com ansible_user=dbadmin
db2.example.com
[production:children]
webservers
databases
[production:vars]
ansible_python_interpreter=/usr/bin/python3
ansible_connection=ssh
YAML Inventory
# inventory/hosts.yml
all:
children:
webservers:
hosts:
web1.example.com:
web2.example.com:
ansible_host: 192.168.1.10
databases:
hosts:
db1.example.com:
ansible_user: dbadmin
db2.example.com:
production:
children:
webservers:
databases:
vars:
ansible_python_interpreter: /usr/bin/python3
ansible_connection: ssh
Dynamic Inventory
#!/usr/bin/env python3
# inventory/aws_ec2.py
import json
import boto3
def get_inventory():
ec2 = boto3.client('ec2', region_name='us-east-1')
response = ec2.describe_instances(Filters=[
{'Name': 'instance-state-name', 'Values': ['running']}
])
inventory = {
'_meta': {'hostvars': {}},
'all': {'hosts': []},
'webservers': {'hosts': []},
'databases': {'hosts': []},
}
for reservation in response['Reservations']:
for instance in reservation['Instances']:
ip = instance['PrivateIpAddress']
tags = {tag['Key']: tag['Value'] for tag in instance.get('Tags', [])}
inventory['all']['hosts'].append(ip)
inventory['_meta']['hostvars'][ip] = {
'ansible_host': ip,
'instance_id': instance['InstanceId'],
'instance_type': instance['InstanceType'],
}
# Group by role tag
role = tags.get('Role', '')
if role in inventory:
inventory[role]['hosts'].append(ip)
return inventory
if __name__ == '__main__':
print(json.dumps(get_inventory(), indent=2))
Templates (Jinja2)
{# templates/app.conf.j2 #}
# Application configuration for {{ app_name }}
# Generated by Ansible on {{ ansible_date_time.iso8601 }}
[server]
host = {{ ansible_default_ipv4.address }}
port = {{ app_port }}
workers = {{ ansible_processor_vcpus }}
[database]
host = {{ db_host }}
port = {{ db_port }}
name = {{ db_name }}
user = {{ db_user }}
password = {{ db_password }}
[cache]
enabled = {{ cache_enabled | default(true) | lower }}
{% if cache_enabled | default(true) %}
backend = redis
redis_host = {{ redis_host }}
redis_port = {{ redis_port }}
{% endif %}
[features]
{% for feature, enabled in features.items() %}
{{ feature }} = {{ enabled | lower }}
{% endfor %}
{% if environment == 'production' %}
[production]
debug = false
log_level = warning
{% else %}
[development]
debug = true
log_level = debug
{% endif %}
Variables and Facts
Variable Precedence (low to high)
- Role defaults
- Inventory file/script group vars
- Inventory group_vars/all
- Playbook group_vars/all
- Inventory group_vars/*
- Playbook group_vars/*
- Inventory file/script host vars
- Inventory host_vars/*
- Playbook host_vars/*
- Host facts
- Play vars
- Play vars_prompt
- Play vars_files
- Role vars
- Block vars
- Task vars
- Extra vars (-e flag)
Using Variables
---
- name: Variable examples
hosts: all
vars:
app_name: myapp
app_version: 1.0.0
vars_files:
- vars/common.yml
- 'vars/{{ environment }}.yml'
tasks:
- name: Load variables from file
include_vars:
file: 'vars/{{ ansible_distribution }}.yml'
- name: Set fact
set_fact:
full_app_name: '{{ app_name }}-{{ app_version }}'
- name: Register output
command: hostname
register: hostname_output
- name: Use registered variable
debug:
msg: 'Hostname is {{ hostname_output.stdout }}'
- name: Access facts
debug:
msg: |
OS: {{ ansible_distribution }} {{ ansible_distribution_version }}
Kernel: {{ ansible_kernel }}
CPU: {{ ansible_processor_vcpus }} cores
Memory: {{ ansible_memtotal_mb }} MB
IP: {{ ansible_default_ipv4.address }}
Error Handling
---
- name: Error handling examples
hosts: all
tasks:
- name: Task that might fail
command: /bin/false
ignore_errors: yes
- name: Task with custom error handling
block:
- name: Try to start service
systemd:
name: myapp
state: started
rescue:
- name: Log error
debug:
msg: 'Failed to start myapp'
- name: Try alternative
systemd:
name: myapp-fallback
state: started
always:
- name: This always runs
debug:
msg: 'Cleanup task'
- name: Assert condition
assert:
that:
- ansible_memtotal_mb >= 2048
- ansible_processor_vcpus >= 2
fail_msg: 'Server does not meet minimum requirements'
- name: Fail when condition
fail:
msg: 'Production deployment requires version tag'
when:
- environment == 'production'
- app_version == 'latest'
- name: Changed when condition
command: /usr/local/bin/check_status.sh
register: result
changed_when: "'updated' in result.stdout"
failed_when: result.rc not in [0, 2]
Ansible Vault
# Create encrypted file
ansible-vault create secrets.yml
# Edit encrypted file
ansible-vault edit secrets.yml
# Encrypt existing file
ansible-vault encrypt vars/production.yml
# Decrypt file
ansible-vault decrypt vars/production.yml
# View encrypted file
ansible-vault view secrets.yml
# Rekey (change password)
ansible-vault rekey secrets.yml
# secrets.yml - what `ansible-vault view secrets.yml` shows you.
# On disk this file is ciphertext; it is only ever plaintext in memory and in
# your editor during `ansible-vault edit`. Never commit the decrypted form.
---
db_password: "{{ lookup('env', 'DB_PASSWORD') }}"
api_key: "{{ lookup('env', 'API_KEY') }}"
ssl_key: "{{ lookup('env', 'SSL_PRIVATE_KEY') }}"
# The same file at rest, after `ansible-vault encrypt`:
# $ANSIBLE_VAULT;1.1;AES256
# 66386439653236336462626566653063336164663966303231363934653561363964363833313662
# ...
# Use in playbook
---
- name: Deploy with secrets
hosts: production
vars_files:
- secrets.yml
tasks:
- name: Configure database
template:
src: db.conf.j2
dest: /etc/db.conf
no_log: yes # Don't log sensitive data
# Run playbook with vault password
ansible-playbook playbook.yml --ask-vault-pass
# Use password file
ansible-playbook playbook.yml --vault-password-file ~/.vault_pass
# Use multiple vault IDs
ansible-playbook playbook.yml --vault-id prod@prompt --vault-id dev@~/.vault_dev
Testing
Molecule (Role Testing)
# Install molecule
pip install molecule molecule-docker
# Initialize molecule
cd roles/myapp
molecule init scenario
# Run tests
molecule test
# Test workflow
molecule create # Create test instances
molecule converge # Run playbook
molecule verify # Run tests
molecule destroy # Cleanup
# molecule/default/molecule.yml
---
dependency:
name: galaxy
driver:
name: docker
platforms:
- name: ubuntu
image: geerlingguy/docker-ubuntu2004-ansible
pre_build_image: yes
provisioner:
name: ansible
verifier:
name: ansible
Anti-Patterns to Avoid
❌ Not using roles: Organize code in reusable roles ❌ Shell commands everywhere: Use modules when available ❌ Hardcoded values: Use variables ❌ No error handling: Use blocks, rescue, always ❌ Storing secrets in plaintext: Use Ansible Vault ❌ Not testing: Use molecule for role testing ❌ Ignoring idempotency: Tasks should be safe to run multiple times ❌ Complex playbooks: Break into smaller, focused playbooks
Reference Documentation
Detailed material lives alongside this skill and is read on demand:
- Best Practices — Playbook Organization, Idempotency, Performance, Security
- Playbooks — Basic Playbook, Advanced Playbook, Conditionals and Loops
- Roles — Role Structure, Example Role, Role Dependencies
Resources
- Ansible Documentation: https://docs.ansible.com/
- Ansible Galaxy: https://galaxy.ansible.com/
- Molecule: https://molecule.readthedocs.io/
- Best Practices: https://docs.ansible.com/ansible/latest/user_guide/playbooks_best_practices.html