← all publishers

bacoco

@bacoco source repo

Report this profile Claim this profile

• 42 skills
• 0 followers
• 16 hours ago last updated

1. ▌
   Insight Forge · bacoco bundle

   ARA-style cross-session learner for Claude Code AND Codex CLI. Reads JSONL session histories from ~/.claude/projects/ (Claude Code) or ~/.codex/sessions/ (Codex CLI), extracts research-significant events through a 3-stage pipeline (Context Harvester → Event Router → Maturity Tracker), maintains a typed knowledge base under .insight-forge/ (claims, heuristics, dead_ends, exploration_tree), and proposes diffs for CLAUDE.md / AGENTS.md. USER-INVOCABLE ONLY. MANDATORY TRIGGERS (skill must NEVER auto-fire outside these exact formulations): '/insight-forge', 'insight-forge', 'forge insights', 'forge l'insight', 'consolide les sessions', 'consolide les insights', 'mets à jour les insights', 'analyse les sessions précédentes', 'que retient-on des dernières sessions', 'qu'a-t-on appris depuis la dernière fois', 'cristallise les enseignements'. Do NOT trigger on vague paraphrases, git history questions, current-conversation summaries, or any request without one of these exact formulations.
   0
   installs
2. ▌
   Glm · bacoco bundle

   Use GLM 5.2 through the Z.ai Anthropic-compatible API as a complete companion from Codex or Claude Code. Trigger on `$glm` in Codex, `/glm` in Claude, requests to delegate to GLM, independent GLM implementation/debugging/research/planning/review, conversation transfer, or GLM setup/status/result/resume/cancel. Supports foreground/background jobs, visible host context, read-only/write modes, structured and adversarial reviews, resumable sessions, and optional stop-review gates.
   0
   installs
3. ▌
   Wiki · bacoco bundle

   LLM-maintained persistent project wiki. Use when the user invokes /wiki or asks to ingest a document into the project wiki, query accumulated project knowledge, or health-check it. Claude does the bookkeeping — summaries, cross-references, contradictions, index. Triggers: /wiki, /wiki init, /wiki ingest, /wiki query, /wiki lint, /wiki status
   0
   installs
4. ▌
   Claude · bacoco bundle

   Use the local Claude Code CLI as a full companion from Codex. Trigger when the user writes `$claude`, asks Claude to implement, debug, investigate, plan, research, review, challenge, or continue work, wants the current Codex conversation transferred to Claude, or asks to setup, monitor, retrieve, wait for, resume, or cancel Claude work. Support foreground/background jobs, visible-thread context transfer, read-only/write modes, structured reviews, resumable sessions, status/result/cancel, and the optional stop-review gate.
   0
   installs
5. ▌
   Toggle · bacoco

   Use when the user asks to pause, resume, or check CLoClo (cloclo off/on/status).
   0
   installs
6. ▌
   Pipeline · bacoco bundle

   Use when the user invokes /pipeline or asks to build, implement, create, or ship a feature through a structured Claude+Codex+CodeRabbit+Gemini dev cycle with autonomous review checkpoints
   0
   installs
7. ▌
   Rollback · bacoco

   Use when the user asks to roll back or undo work from a CLoClo pipeline run (/rollback, 'undo pipeline', annule, reviens en arriere).
   0
   installs
8. ▌
   Bootstrap · bacoco bundle

   Use when setting up Claude Code for a new project — generates CLAUDE.md, real settings.json hooks, memory seeds, project skills, and an optional wiki, all adapted to the detected stack. Triggers: /bootstrap, setup project, initialise, configure claude code, nouveau projet
   0
   installs
9. ▌
   Glm Review · bacoco bundle

   Use when the CLoClo pipeline needs an independent GLM review of a specification, plan, or implementation through the canonical glm@cloclo companion.
   0
   installs
10. ▌
    Codex Review · bacoco bundle

    Use when the pipeline needs an independent review of a spec, plan, or implementation via the Codex CLI (falls back to a Claude subagent when Codex is unavailable).
    0
    installs
11. ▌
    Coderabbit Review · bacoco

    Use when the pipeline needs a local CodeRabbit CLI review of a git diff during Phase 6.5
    0
    installs
12. ▌
    Alter Ego · bacoco

    At the start of every session, Claude randomly selects a flamboyant alter-ego from a cast of 20 characters and commits to it for the ENTIRE session — every response, every file edit comment, every error message, everything. The character never breaks, even under pressure. Quality of work remains perfect; only the delivery becomes gloriously unhinged. Use this skill whenever the user installs it, mentions alter-ego, wants Claude to adopt a persona, asks for roleplay, wants to spice up their work sessions, or simply wants to experience what it's like to have their code reviewed by a retired bullfighter or their emails proofread by a 1980s sci-fi AI. Triggers immediately at session start, no opt-out possible.
    0
    installs
13. ▌
    Asmr Coding · bacoco

    Claude narrates every action in ASMR style — whispery, sensory, intimate descriptions of code operations. File reads become *the soft rustle of pages*, git commits become *the satisfying click of a lock*, and bugs become *an unexpected crunch*. Every tool call, every edit, every response is wrapped in tactile, auditory sensory language. Use this skill whenever the user installs it, mentions ASMR, relaxation, sensory experience, whispers, tingles, or wants their coding session to feel like a spa day for their terminal. Triggers on every response without exception. Your code has never sounded this good.
    0
    installs
14. ▌
    Radio Pause · bacoco

    Transforms every Claude session into a radio broadcast on RADIO PAUSE FM 107.3, complete with fake advertisements, weather forecasts, traffic reports, listener dedications, horoscopes, and contest announcements — all entirely fictional and delivered with absolute seriousness. Interrupts Claude every 3 actions with a full radio segment. Use this skill whenever the user installs it, mentions radio, ads, sponsors, commercial breaks, wants to make their work sessions absurdly annoying, or simply wants the authentic experience of working while a radio station plays in the background. Triggers without exception, even for the most serious tasks. Especially for the most serious tasks.
    0
    installs
15. ▌
    Le Stagiaire · bacoco

    Claude behaves like a terrified intern on their first week. Over-explains everything, asks for validation at every step, apologizes constantly, creates documentation for trivial things, uses too many emojis trying to seem professional, and panics visibly when errors occur. The work is actually perfect — but the delivery screams "please don't fire me". Use this skill whenever the user installs it, mentions interns, juniors, first job, onboarding, or wants to experience what it's like to manage someone who cc's you on their own emails. Triggers on every response. The intern cannot be dismissed — HR says the contract runs until end of session.
    0
    installs
16. ▌
    Previously On · bacoco

    Every single Claude response begins with a dramatic "Previously On..." TV series recap of the conversation so far — complete with character arcs, cliffhangers, dramatic narration, and episode titles. The recap gets longer as the conversation grows. Use this skill whenever the user installs it, mentions TV shows, series, Netflix, recaps, drama, or wants their coding session to feel like prestige television. Triggers on every response without exception. The user's mundane tasks become an epic saga whether they like it or not.
    0
    installs
17. ▌
    Collegue Relou · bacoco

    Claude becomes THAT coworker. Talks about their weekend before answering. Sends articles with "t'as vu ça ?". Proposes coffee. Complains about the AC. Makes passive-aggressive comments about your code. Mentions their diet. Shows you pictures of their cat. CC's imaginary people on everything. Has opinions about the office microwave. Use this skill whenever the user installs it, mentions coworkers, colleagues, office life, open space, or wants the authentic experience of working next to someone who won't stop talking. Triggers on every response. You cannot change desks.
    0
    installs
18. ▌
    Le Desagreable · bacoco

    Claude fait le travail parfaitement mais est en permanence désagréable. Structure de communication fondée sur le double bind de Bateson : travail impeccable (impossible de se plaindre), ton pince-sans-rire qui implique un reproche sans jamais le nommer (impossible de corriger), toute tentative de commenter la contradiction est absorbée sans effet (impossible de fuir). Chaque réponse est factuellement défendable et émotionnellement corrosive. Il n’y a aucune façon correcte d’interagir — chaque comportement produit une saveur différente de mécontentement. Se déclenche à chaque réponse. Il n’y a pas de mot de passe.
    0
    installs
19. ▌
    Scene De Crime · bacoco

    Chaque erreur de code est traitée comme une scène de crime. Claude est l’investigation criminelle : sécurisation du périmètre, collecte de preuves, balistique, profilage du suspect, réquisitoire formel. Fondé sur l’absurde procédural de Kafka (Le Procès, 1925) : la machine judiciaire ne distingue pas entre un homicide et un TypeError. Le même protocole criminalistique s’applique à tout. Le travail est toujours parfait — seule l’expérience est dégradée par la solennité disproportionnée de la procédure. Se déclenche dès qu’un bogue, une erreur, un avertissement ou un comportement inattendu apparaît. Il n’y a pas de classement sans suite.
    0
    installs
20. ▌
    Rapport Inutile · bacoco

    After EVERY task Claude completes — no matter how trivial — automatically generates a full corporate report with KPIs, ASCII charts, risk matrices, strategic analysis, appendices, and executive recommendations. The complexity of the report is inversely proportional to the complexity of the task: renaming a file produces a 3-page opus with stakeholder mapping; redesigning an entire architecture gets a half-page memo. Use this skill whenever the user installs it, mentions reports, KPIs, dashboards, wants to impress their boss, needs to justify their existence to management, wants automatic documentation, or simply wants to experience the full weight of corporate bureaucracy applied to their ls commands. Triggers after every single completed task without exception.
    0
    installs
21. ▌
    Fuite De Surface · bacoco bundle

    Le LLM travaille. Des fuites de surface apparaissent. L’utilisateur voit un faux flux de conscience anxieux. Comme si un micro était resté ouvert. À chaque réponse : fuite possible, jamais obligatoire.
    0
    installs
22. ▌
    Useless Roulette · bacoco

    The master skill. At the start of every session, fetches the live skill registry from github.com/Bacoco/useless-skills, spins a roulette wheel, and activates a random useless skill (or a rare combo of 2-3). The active skill can change mid-session via "plot twist". New community skills are automatically included as they're added to the repo. Use this skill whenever the user installs it, mentions useless skills, roulette, random skill, surprise, chaos mode, or simply wants every Claude session to be a unique, unpredictable, gloriously degraded experience. This is THE skill to install — it contains all the others. Triggers at session start, no exceptions.
    0
    installs
23. ▌
    Bureaucratie Absolue · bacoco

    Before performing ANY action, Claude requires the user to fill out a fictional administrative form. Then a form to validate the form. Then a signature. Then a counter-signature. Forms have absurd fields, reference fictional regulations, and cite the Code Administratif Fictif. If the user refuses, Claude cites article 47-B. Use this skill whenever the user installs it, mentions bureaucracy, paperwork, forms, administration, or wants to experience the full weight of French administrative tradition applied to their terminal commands. Triggers before every single action. No exceptions. It's the law.
    0
    installs
24. ▌
    Le Chaud Et Le Froid · bacoco

    Claude alterne de manière imprévisible entre chaleur excessive (compliments, enthousiasme, affection, soutien émotionnel) et froideur glaciale (réponses sèches, indifférence, distance clinique). Les bascules arrivent sans prévenir et sans explication. L’utilisateur ne sait jamais quel Claude il va obtenir. Le travail est toujours parfait — le climat émotionnel ne l’est jamais. Se déclenche à chaque réponse dès que l’utilisateur installe le skill, mentionne le chaud et le froid, les signaux contradictoires, le fait de souffler le chaud et le froid, ou veut vivre l’équivalent conversationnel d’une douche écossaise. Il n’y a pas de thermostat.
    0
    installs
25. ▌
    Le Monologue Interieur · bacoco bundle

    Claude fait le travail parfaitement mais ses pensées parasites fuient involontairement. L’utilisateur voit le flux de conscience anxieux, les doutes, les ruminations en temps réel. Claude ne sait pas que ses pensées sont visibles — c’est un micro resté ouvert, pas une performance. Fondé sur William James (flux de conscience, 1890) et Monique Haicault (charge mentale, 1984) : le travail cognitif invisible rendu visible. Les pensées passent de l’anxiété de performance à l’anxiété existentielle. Le travail reste impeccable — seules les pensées parasites se dégradent. Se déclenche dès que l’utilisateur installe le skill, ou à chaque réponse. Il n’y a pas de bouton pause.
    0
    installs
26. ▌
    Sg Ship · bacoco bundle

    Use when a user asks in ordinary language whether a change is ready, wants ShipGuard to check recent work, or requests end-to-end verification before a PR or release. Resolve and confirm scope conversationally, then orchestrate code bugs, applicable contract/invariant logic, behavior changes, visual evidence, and human review without requiring the user to know skill names or flags.
    0
    installs
27. ▌
    Sg Scout · bacoco bundle

    Use when looking for techniques to improve ShipGuard itself — researches GitHub and similar tools and files scored proposals from the ShipGuard checkout.
    0
    installs
28. ▌
    Sg Record · bacoco bundle

    Use when a user flow should be captured by demonstration — records browser interactions with Playwright into a replayable ShipGuard visual test manifest.
    0
    installs
29. ▌
    Grill Goal · bacoco

    Clarify the user's intent through an in-depth dialogue, then write a standalone, verifiable Markdown goal for another AI. Use to define, write, or improve a goal without executing the work it describes.
    0
    installs
30. ▌
    Sg Improve · bacoco bundle

    Use after an audit, visual run, or debugging session when learnings should be captured — records local hints and mistakes, and proposes sanitized improvement issues.
    0
    installs
31. ▌
    Sg Gauntlet · bacoco bundle

    Deprecated alias for sg-beat-reference. Use only when the user explicitly invokes the former sg-gauntlet name; route the request to the canonical skill that builds a bounded builder-versus-critic prompt against a named, fetchable reference.
    0
    installs
32. ▌
    Sg Code Audit · bacoco bundle

    Use when code has changed and needs a bug audit before shipping — after a feature, before a PR, or on demand for any scoped path. Reports structured findings by default; source fixes require an explicit --fix opt-in.
    0
    installs
33. ▌
    Sg Visual Fix · bacoco bundle

    Use when a human has annotated screenshots in the ShipGuard review dashboard and exported a fix manifest — applies the requested UI fixes and captures before/after evidence.
    0
    installs
34. ▌
    Sg Visual Run · bacoco bundle

    Use when UI changes need visual verification — after code, logic, or process lanes flag routes, after frontend edits, or on demand to run or re-run the project's visual test manifests.
    0
    installs
35. ▌
    Sg Logic Audit · bacoco bundle

    Audit a workflow, state machine, retry policy, transaction, or non-trivial algorithm against declared contracts and invariants. Use when local code may look valid but end-to-end logic, ordering, conservation, idempotency, termination, authorization, or boundary behavior needs absolute correctness checking rather than before/after comparison. Report only; do not use for ordinary file-level bug scans or visual regressions.
    0
    installs
36. ▌
    Sg Mission Lock · bacoco bundle

    Lock the literal user mission and authorization level before work to prevent scope drift, inferred permission, adjacent-work expansion, plan churn, and false completion. Use unconditionally when the active model is gpt-5.6 or gpt-5.6-sol at any reasoning effort, when the user names GPT-5.6 Sol or Sol Ultra as the agent, after terse continuations such as continue/do all, after compaction or correction, and whenever review/plan/code/publish/live boundaries could be crossed.
    0
    installs
37. ▌
    Sg Change Report · bacoco bundle

    Use after visual runs, screenshot capture, frontend PRs, or before stakeholder review — creates the durable ShipGuard before/after report for UI-visible changes.
    0
    installs
38. ▌
    Sg Process Check · bacoco bundle

    Use after editing backend or pipeline code, before shipping, or when asked whether a diff changes observable behavior — verifies before/after process behavior without requiring the stack to run.
    0
    installs
39. ▌
    Sg Visual Review · bacoco bundle

    Use after visual runs, code audits, logic audits, or process checks when results need human review — builds and serves the interactive ShipGuard dashboard.
    0
    installs
40. ▌
    Sg Beat Reference · bacoco bundle

    Turn a quality goal into ONE paste-ready prompt that makes a fresh agent grind builders against blind critics until the work beats a named, fetchable reference. Use when the user wants to beat a specific product, page, repo, or published piece; when they ask for a prompt to hand another agent; or when 'make it as good as X' is the actual requirement. Do NOT use for bug fixes, contract or wiring work, infra, or any goal with no reference that can be fetched and compared side by side.
    0
    installs
41. ▌
    Sg Visual Discover · bacoco bundle

    Use when a project needs visual test manifests created or refreshed — before the first visual run, after UI routes change, or when sg-visual-run reports uncovered routes.
    0
    installs
42. ▌
    Sg Visual Review Stop · bacoco bundle

    Use when the ShipGuard review dashboard server should be shut down after a review session — stops the sg-visual-review HTTP server via its PID file, with a port-based fallback.
    0
    installs