mirror of https://github.com/personamanagmentlayer/pcl.git synced 2026-09-14 15:40:22 +08:00

Files

T

ANGX 4e07a6a874 feat(stdlib)!: Agent Skills v1.0 conformance, resolver fix, and 17 new skills (#43 )

* 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withdrawn.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.

2026-09-05 04:35:30 +02:00

5.5 KiB

Raw Permalink Blame History

name, version, description, category, tags, allowed-tools, metadata

name

version

description

Serverless Expert

Design and implement production-grade serverless applications with optimal performance, cost efficiency, and scalability.

Learning Objectives

Master serverless architecture patterns and best practices
Build event-driven systems with AWS Lambda and Azure Functions
Implement Function-as-a-Service (FaaS) applications
Design for cold starts and optimization strategies
Integrate serverless with API Gateway and event sources

Prerequisites

Strong cloud platform knowledge (AWS/Azure/GCP)
Understanding of event-driven architectures
Knowledge of microservices patterns
Familiarity with Infrastructure as Code

Core Concepts

Function-as-a-Service (FaaS)

Cloud computing model where functions execute in response to events without managing servers. Platform automatically provisions, scales, and manages infrastructure based on demand.

Event-Driven Architecture

Design paradigm where functions react to events from various sources (HTTP requests, database changes, file uploads, queues). Enables loose coupling and scalability.

Cold Starts & Warm Starts

Cold start occurs when function executes for first time or after idle period, requiring initialization. Warm starts reuse existing execution environment for faster response times.

Serverless Orchestration

Coordination of multiple serverless functions in workflows using services like AWS Step Functions or Azure Durable Functions. Enables complex business logic across distributed functions.

Serverless Security

Security considerations including IAM roles, function permissions, API authentication, secrets management, and VPC networking for serverless workloads.

Best Practices

Function Design

Keep functions small and single-purpose
Design for idempotency to handle retries safely
Use environment variables for configuration
Implement proper error handling and logging
Return appropriate HTTP status codes
Version functions for gradual rollouts
Minimize cold start impact with provisioned concurrency

Performance Optimization

Reuse connections and clients outside handler
Use connection pooling for databases
Minimize package size and dependencies
Enable Lambda layers for shared code
Optimize memory allocation (CPU scales with memory)
Use async/await for concurrent operations
Implement caching strategies

Event-Driven Patterns

Use dead letter queues for failed events
Implement exponential backoff for retries
Design for eventual consistency
Use event sourcing for audit trails
Implement circuit breakers for external services
Batch process events when possible
Use fan-out patterns for parallel processing

Cost Optimization

Right-size memory allocation
Use reserved concurrency carefully
Implement request throttling
Archive logs to S3 after retention period
Use S3 lifecycle policies
Monitor and alert on cost anomalies
Consider compute savings plans

Anti-Patterns

Common Mistakes

Long-running functions exceeding timeout limits
Not handling cold starts appropriately
Synchronous processing of independent tasks
Storing state in function memory
Hardcoding configuration values
Not implementing proper monitoring
Ignoring concurrency limits
Recursive function calls without limits

Design Issues

Functions doing too much (violating single responsibility)
Tight coupling between functions
Not using infrastructure as code
Inadequate error handling and retries
Missing dead letter queues
Not implementing tracing
Ignoring security best practices
Poor secret management

Reference Documentation

Detailed material lives alongside this skill and is read on demand:

Code Examples — AWS Lambda with Advanced Patterns, Serverless Framework Configuration

Resources

Serverless Platforms

AWS Lambda - Leading FaaS platform
Azure Functions - Microsoft serverless
Google Cloud Functions
Cloudflare Workers - Edge computing
Vercel Functions - Frontend-focused
Netlify Functions

Frameworks & Tools

Serverless Framework - Multi-cloud IaC
AWS SAM - AWS native framework
Terraform - Infrastructure as code
Pulumi - Modern IaC with programming languages
LocalStack - Local AWS emulation
serverless-offline - Local development

Monitoring & Observability

AWS X-Ray - Distributed tracing
CloudWatch - Logs and metrics
Datadog - APM and monitoring
New Relic - Observability platform
Lumigo - Serverless monitoring
Thundra - Debugging and profiling

Learning Resources

AWS Well-Architected Serverless Lens
Serverless Architecture Patterns
Azure Serverless Computing Cookbook
Serverless Stack - Full-stack tutorial
Production-Ready Serverless course
AWS Lambda Power Tuning

Part of the PCL Standard Library - Build scalable, cost-effective applications without managing servers.

5.5 KiB Raw Permalink Blame History