Agent Skills by chrono-meta
Showing 39 vetted skills indexed across 1 GitHub repositories.
cross-ecosystem-synergy-detection
Detect compatible synergy pairs among installed plugins and cross-CLI tools.
goal-quench
Estimate token budgets, alert on thresholds, and verify output quality for /goal sessions.
return-path-gate
Audit SKILL.md files for unclosed fire-and-forget skill chains.
plugin-recommender
Search internal and external plugin ecosystems to recommend validated plugins for task descriptions.
apex-review
Evaluates technical proposals and generates HTML briefing decks with per-persona approval criteria.
context-bridge-dispatch
Coordinate parallel AI coding agents with context injection and task boundaries.
corpus-grounding-expander
Ingest multi-version public-domain corpora into a unified verbatim grounding store.
sim-conductor
Automate multi-persona simulation workflows for artifact validation and triage.
steel-quench
Run multi-wave adversarial reviews on near-complete artifacts and produce residual risk cards.
phantom-quench
Back-trace verifiable claims in AI-generated artifacts to declared sources.
field-harvest
Scan git commit history to detect reusable patterns and log session work.
marketplace-gate
Audit repositories against a 5-point marketplace inclusion checklist.
video-ingest
Ingest video content from YouTube using capability-routed extraction methods.
context-doctor
Diagnose token waste in Claude Code sessions and prescribe context optimizations.
salience-splitter
Split bloated context assets into lean always-loaded and on-demand layers.
agent-composer
Map multi-part workflows to optimal AI agent combinations across Claude Code and Codex.
pipeline-conductor
Chain four Forge Harness verification pipelines into a gated sequential sweep.
prompt-regression
Detect silent behavioral regressions in Claude Code harness configurations after rule or skill edits.
self-marketing-lint
Detect promotional language in Forge Harness documentation and metadata.
asset-placement-gate
Route proposed AI assets to storage locations using a 4-criteria evaluation framework.
harness-doctor
Diagnose structural health, complexity, drift, and pattern issues in Claude Code project harnesses.
memory-hygiene
Scan memory markdown files and re-verify stale external references.
edit-manifest
Verify harness asset edits against declared predictions in edit_manifest.yaml.
public-surface-audit
Scan git-tracked files for operator-private tokens and output JSON reports.