Instructions file CodexOpenCode
AGENTS.md instructions for byPawel/tachibot-mcp, covering agents.md, project overview, architecture principles, solid principles and dry (don't repeat yourself).
15 2d ago A 5,917 tokens
algo
02Skill Claude CodeCodex
Algorithm analysis with parallel multi-model reasoning — deepseekalgo (lead), qwenalgo, qwenreason, and minimaxcode tackle your problem from different angles.
15 2d ago A 34 tokens
audit
03Skill Claude CodeCodex
Use when the user wants a security review of code or a diff — OWASP/CWE findings with severity, taint/data-flow analysis, and concrete fixes via securityreview.
15 2d ago A 36 tokens
blueprint
04Skill Claude CodeCodex
Multi-model implementation planning — creates bite-sized TDD plans using plannermaker's council pipeline with goal-oriented checkpoints.
15 2d ago A 25 tokens
breakdown
05Skill Claude CodeCodex
Break down complex problems before implementation using multi-model reasoning and prompt techniques.
15 2d ago A 16 tokens
council
06Skill Claude CodeCodex
Deep multi-model council with research, adversarial debate, sequential reasoning, and final synthesis. For architecture decisions and complex tradeoffs.
15 2d ago A 30 tokens
decompose
07Skill Claude CodeCodex
Decompose problems into sub-problems, then deep-dive each one with sequential multi-model reasoning.
15 2d ago A 22 tokens
focus
08Skill Claude CodeCodex
Multi-model reasoning with modes like deep-reasoning, architecture-debate, research, analyze.
15 2d ago A 20 tokens
judge
09Skill Claude CodeCodex
Use for decisions or judgments worth multiple independent perspectives — multi-model council with parallel analysis, search grounding, and synthesis (30-60s); for a quick single-call verdict use the jury tool directly.
15 2d ago A 41 tokens
jury
10Skill Claude CodeCodex
Quick multi-model jury — parallel jurors + Gemini synthesis in one call. Default entry point for judgment tasks.
15 2d ago A 24 tokens
lens
11Skill Claude CodeCodex
Long-context analysis — examine a large document or codebase under a focused lens using active retrieval over Kimi's 1M window, surfacing insights, relations, and inconsistencies.
15 2d ago A 38 tokens
prompt
12Skill Claude CodeCodex
Use when a task would benefit from a structured thinking technique but you're not sure which — recommends the right prompt technique for the intent (debug, spec, refactor, decision, design) and applies it.
15 2d ago A 42 tokens
redteam
13Skill Claude CodeCodex
Use when the user shares or finishes a plan and wants it stress-tested before execution — adversarial multi-model pre-mortem with ranked risks, mitigations, and concrete plan edits.
15 2d ago A 39 tokens
reflect
14Skill Claude CodeCodex
Iterative reflexion loop — generate, critique against EXTERNAL evidence (real tests, search), then revise until it converges. Grounded self-correction, not sycophantic self-review.
15 2d ago A 41 tokens
review
15Skill Claude CodeCodex
Use when code changes are ready for review — a diff exists, the user says "review my changes/PR", or a commit is about to happen. Multi-model diff review (Kimi K3, DeepSeek, GPT-5.6 panel + Gemini judge) with a MERGEABLE verdict.
15 2d ago A 62 tokens
setup
16Skill Claude CodeCodex
Use when TachiBot tools seem missing, a provider isn't working, or the user asks for a setup wizard or to set up/configure TachiBot or its API keys — runs doctor and walks through fixing the gaps.
15 2d ago A 46 tokens
spec
17Skill Claude CodeCodex
Use when a feature request is loose or ambiguous and needs a reviewable spec before planning — turns "add X somehow" into user stories, acceptance criteria, out-of-scope, and open questions via specwriter.
15 2d ago A 44 tokens
tachi
18Skill Claude CodeCodex
Use when the user asks what TachiBot can do, which tools/skills exist, or which API keys are configured — help and discovery entry point.
15 2d ago A 33 tokens
test
19Skill Claude CodeCodex
Use when the user wants tests generated for code or a diff — enumerates edge cases and failure modes first, then emits runnable test code via testgen.
15 2d ago A 32 tokens
think
20Skill Claude CodeCodex
Chain-of-thought reasoning with optional multi-model execution using nextThought.
15 2d ago A 15 tokens
tot
21Skill Claude CodeCodex
Tree-of-Thought reasoning — branch a problem into multiple solution paths, explore each, score and prune branches via a model jury, then synthesize the best. Non-linear reasoning that can backtrack.
15 2d ago A 41 tokens
triage
22Skill Claude CodeCodex
Use when the user hits an error, exception, or stack trace and the cause isn't obvious — returns RANKED root-cause hypotheses with the cheapest discriminating check for each, via debugtriage.
15 2d ago A 43 tokens
write
23Skill Claude CodeCodex
Use when writing a blog post, article, doc, or report that must be fact-grounded and not generic — live research feeds blogwriter, then separate verify (claims vs retrieved passages) and de-generic (voice) gates. Fail-closed with a claim ledger.
15 2d ago A 57 tokens
tachibot-mcp
24MCP server Claude CodeCodexCursor +2
Multi-model AI orchestration with 31 tools, YAML workflows, and 5 token-optimized profiles. Runs locally from the tachibot-mcp npm package. Needs 6 environment variables to run.
15 2d ago A
tokens not measured