agent-capability-analyzer
Agent Capability Analyzer
Overview
Description drift occurs when an agent's frontmatter description no longer matches what the agent actually does. Orchestrators use descriptions for routing decisions — stale descriptions cause misrouting. This skill collects self-reported capabilities from agents and compares them against their static frontmatter descriptions to quantify the gap.
The dataset lives in a LevelDB store (agent-map.db/ relative to $CLAUDE_PROJECT_DIR) with two fields per agent: description (from frontmatter) and capabilities (self-reported). The dump command exports both fields to JSON for analysis.
The canonical dataset location is .claude/audits/agent-map.json.
Invocation Mode
Choose invocation mode before spawning any Tasks. The routing decision is based on how many agents are being checked.
flowchart TD
Start([Capability check requested]) --> Q1{How many agents?}
Q1 -->|1 agent| Single[Single-agent mode]
Q1 -->|2 or more agents| Multi[Multi-agent mode]
More from jamie-bitflight/claude_skills
perl-lint
This skill should be used when the user asks to lint Perl code, run perlcritic, check Perl style, format Perl code, run perltidy, or mentions Perl Critic policies, code formatting, or style checking.
28brainstorming-skill
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using 30+ research-validated prompt patterns.
17work-backlog-item
Use when working, planning, or closing a backlog item. Bridges backlog items to SAM planning with GitHub Issue/Project/Milestone tracking. No args: interactive browser. '#N': load from GitHub Issue #N. Title substring: auto-grooming, RT-ICA gate, GitHub sync, SAM planning. '--auto {title}': autonomous mode — no AskUserQuestion, derives data from research files, logs decisions. 'close {title}': dismiss without completion — reason required (duplicate, out_of_scope, superseded, wontfix, blocked). ADR-9. 'resolve {title}': mark DONE with evidence trail — summary required. ADR-9. 'setup-github': init labels, project, milestone. '--language' and '--stack' select Layer 1/2 profile. STOPS if item has Plan field or RT-ICA returns BLOCKED.
11hooks-guide
Cross-platform hooks reference for AI coding assistants — Claude Code, GitHub Copilot, Cursor, Windsurf, Amp. Covers hook authoring in Node.js CJS and Python, per-platform event schemas, inline-agent hooks and MCP in agent frontmatter, common JSON I/O, exit codes, best practices, and a fetch script to refresh docs from official sources. Use when writing, reviewing, or debugging hooks for any AI assistant.
11add-doc-updater
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
11agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
11