Cogniact Governor
Always-on governance skill for efficient and effective agent cognition and action. Use for reasoning, writing, research, coding, files, artifacts, current-information, safety-sensitive, or multi-step agentic tasks to scope the target, choose the cheapest sufficient thinking and behavior, verify evidence, respect boundaries, and report the best supported outcome.
Ai Dev Loop Sanitize Commits
Sanitize unpushed local git commits from ai-dev-loop R/K loops. Use when a branch has local `R:` or `K:` commits and an agent needs to remove `.ai-dev-loop/*` artifacts, rewrite human-readable commit messages, preserve authors/dates, and prepare history before push or review.
Agent Readability Review
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
High Signal Mode
Token-efficient response shaping that preserves correctness, safety, evidence, exact tokens, language, CTA, and audit handoff.
Best Version Builder
Compare, score, improve, retest, and stop candidate-version work with source-grounded identity, target maps, calibrated objectives, broad category buckets with explicit coverage lenses, validation-tier claim caps, evidence ledgers, recomputable score packets, observability markers, artifact checksums, correction audits, release-content hygiene, behavioral-invariance checks, and anti-compression s…
Best Version Builder
Compare, score, improve, retest, and stop candidate-version work with source-grounded identity, target maps, calibrated objectives, broad category buckets with explicit coverage lenses, validation-tier claim caps, evidence ledgers, recomputable score packets, observability markers, artifact checksums, correction audits, release-content hygiene, and anti-compression safeguards.
Core Coding Agent Behavior
Core coding-agent mechanics — task execution, code editing, verification, communication, context management, and persistent memory. Invoke once at the start of any coding/multi-step agentic session to load the full mechanics (the lean CLAUDE.md keeps only the always-on governor + cross-cutting guards).
High Signal Mode
Compress answers with maximum signal while preserving safety, evidence, exact tokens, language, CTA, and audit trail.
Context Compressor
Compress context while preserving task-critical state, exact artifacts, validation, language/tone constraints, and handoff continuity. Use for low-token, brief, compression, continuation, or long-thread state-loss risk.
Context Compressor
Compress and conserve conversation context by using terse responses, compact progress updates, explicit context pruning, compact code/content summaries, and concise handoff summaries. Use when the user asks to reduce token usage, avoid excessive context consumption, compress context, summarize current state, keep replies brief, switch to low-token mode, preserve only task-critical facts, or prepa…
Ai Dev Loop
Token-efficient auditable R/K repository loop with module-on-demand runtime details.
Agent Readability Review
Revises operational text for agent execution with minimal wording while preserving intent, safeguards, protected tokens, validation evidence, handoff state, scripts, and localization.
Ai Dev Loop
A Claude skill from cyfung1031/skills.
Agent Readability Review
Improves operational text so AI agents can parse intent, act reliably, and validate completion with the fewest words needed for correct execution.
Benchmark Dataset Builder
Build large, diverse, auditable benchmark datasets and measurement harnesses for evaluating prompts, skills, specs, agents, or candidate versions across scenarios, languages, contexts, and risk levels.
V1 2 0
A Claude skill from cyfung1031/skills.
Agent Readability Review
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
Best Version Builder
Compare, score, synthesize, retest, and plateau-stop candidate versions with source-grounded identity, target maps, calibrated objectives, broad category buckets with explicit coverage lenses, validation-tier claim caps, evidence ledgers, recomputable score packets, observability markers, artifact checksums, correction audits, and anti-compression safeguards.
Context Compressor
Compress context while preserving task-critical state, exact artifacts, verification, language/tone constraints, and handoff continuity. Use for low-token, brief, compression, continuation, or long-thread state-loss risk.
Github Issue Fix Planner
A Claude skill from cyfung1031/skills.
Cogniact Governor
Always-on governance skill for efficient and effective agent cognition and action. Use for reasoning, writing, research, coding, files, artifacts, current-information, safety-sensitive, or multi-step agentic tasks to scope the target, choose the cheapest sufficient thinking and behavior, verify evidence, respect boundaries, and report the best supported outcome.
Advisory Suggestions
Neutral options with safety boundaries, agency-preserving language, source/uncertainty handling, localization, validation, and audit hooks.
Advisory Suggestions
purpose - neutral options
Agent Readability Review
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
Context Compressor
Compress and conserve conversation context by using terse responses, compact progress updates, explicit context pruning, compact code/content summaries, and concise handoff summaries. Use when the user asks to reduce token usage, avoid excessive context consumption, compress context, summarize current state, keep replies brief, switch to low-token mode, preserve only task-critical facts, or prepa…
Context Compressor
Compress context while preserving task-critical state, exact artifacts, validation, language/tone constraints, and handoff continuity. Use for low-token, brief, compression, continuation, or long-thread state-loss risk.
Advisory Suggestions
Concise neutral options with explicit applicability, safety redirects, agency-preserving wording, evidence/uncertainty handling, full-language localization, exact preservation, validation checklist, audit footer, and regression harness.
Cogniact Governor
Always-on governance skill for efficient and effective agent cognition and action. Use for reasoning, writing, research, coding, files, artifacts, current-information, safety-sensitive, or multi-step agentic tasks to scope the target, choose the cheapest sufficient thinking and behavior, verify evidence, respect boundaries, and report the best supported outcome.
Agent Readability Review
Improves operational text so AI agents can parse intent, act reliably, preserve safeguards, and validate completion with the fewest words needed for correct execution.
High Signal Mode
Compress answers without losing safety, evidence, exact tokens, CTA, or audit.
Core Coding Agent Behavior
Core always-on coding-agent behavior bundle — task execution, code editing, verification, communication, context management, and persistent memory. Load for every coding/agentic session; combined variant of the six individual ai-skills.
Ai Dev Loop Sanitize Commits
Sanitize unpushed local git commits from ai-dev-loop R/K loops. Use when a branch has local `R:` or `K:` commits and an agent needs to remove `.ai-dev-loop/*` artifacts, rewrite human-readable commit messages, preserve authors/dates, and prepare history before push or review.
Context Compressor
Compress and conserve conversation context by using terse responses, compact progress updates, explicit context pruning, compact code/content summaries, and concise handoff summaries. Use when the user asks to reduce token usage, avoid excessive context consumption, compress context, summarize current state, keep replies brief, switch to low-token mode, preserve only task-critical facts, or prepa…
Ai Dev Loop
Token-efficient auditable R/K repository loop.