A French-language CV-writing skill for improving a résumé for both ATS software and AI or recruiter screening. An ATS is a system that reads and filters job applications.

Use it to tailor a CV to a job posting, identify honestly addressable keyword gaps, check claims, scan for screening problems, and render or verify the résumé.

It helps explain genuine experience clearly to automated résumé readers and recruiters without hiding text, stuffing keywords, or inventing claims.

decroche — Skill for Claude Code and Codex by Casius999

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Casius999/decroche-mcp --skill decroche

Clone the repo

git clone --depth 1 https://github.com/Casius999/decroche-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/casius999/decroche-mcp/decroche.svg)](https://agentmods.dev/skills/casius999/decroche-mcp/decroche)

Your own site

<a href="https://agentmods.dev/skills/casius999/decroche-mcp/decroche"><img src="https://agentmods.dev/badge/skills/casius999/decroche-mcp/decroche.svg" alt="Measured on agentmods" height="20"></a>

Per session 314 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,530 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00314	$0.02530
Opus 5	$0.00157	$0.01265
Sonnet 5	$0.00063	$0.00506
Haiku 4.5	$0.00031	$0.00253

Measured 7d ago against content hash cec5f9b1043a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decroche scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/decroche/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

decroche — CV impossible à écarter (honnête)

Thèse (pourquoi ce skill existe)

En 2026 un CV affronte deux lecteurs : un parseur ATS (structure) ET un screener LLM (Workday Illuminate, Greenhouse AI, iCIMS Copilot, Ashby, ou un recruteur qui colle le CV dans ChatGPT/Claude). Battre l'un ne suffit pas. Ce skill optimise pour les deux, par le mérite réel — jamais par la triche (détectée en 2026 → disqualification).

Bornes d'intégrité (NON négociables)

❌ JAMAIS de texte blanc/caché, bourrage de mots-clés, injection de prompt anti-screener, métriques inventées.
✅ Mots-clés alignés sur des compétences réelles ; chiffres réels (demandés au candidat) ; preuves vérifiables.
Quand une métrique manque : demande-la au candidat (voir templates/metrics-interview.md). N'invente jamais.
match_keyword_gap distingue addable_honestly (compétence présente mais non formulée → resurface) de genuinely_missing (absente → ne pas fabriquer ; suggère de l'acquérir, pas de mentir).

Prérequis

Serveur MCP decroche-mcp connecté. Outils disponibles (noms montés) : cv_parse, cv_xyz_scaffold, cv_verify_claims, cv_render · ats_parse_sim, ats_redflag_scan, ats_screener_brief, ats_score_report · match_score, match_keyword_gap · market_get, market_set, market_available. Pipeline 360° (P2-P5) : source_search_market + source_* (france_travail/adzuna/jsearch/labonneboite/careerjet/greenhouse/lever/ashby/recruitee…), match_dedupe/match_success_probability/match_company_intel, monitor_* · recruiter_*/network_* · apply_* (resolve_source/prefill/cover_letter/answer_screening/queue_*/send_approved/followup) · analytics_* (track/update_stage/funnel/channel_roi) · interview_* · negotiate_*. Voir references/pipeline.md. Inspecte le schéma live de chaque outil pour les paramètres exacts ; ci-dessous = l'ordre + l'intention.

Workflow — 4 phases

Phase 0 — Cadrage

Demande : le fichier CV (chemin), l'offre (texte ou URL), le marché cible (FR/US/UK/CA).
market_set sur le marché cible (sinon market_get = défaut FR). market_available liste les profils.
cv_parse le CV → JSON Resume + sections + parse_confidence + warnings.
- Si parse_confidence bas ou warning scanned_or_empty → le CV est mal extractible : signale-le, demande une version texte/Word avant d'aller plus loin.

Read the full file on GitHub · 97 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 97 lines · 314 tokens per session scan A cec5f9b1043a

Subscribe to this mod's changes

decroche is a skill published in the GitHub repository Casius999/decroche-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 314 tokens to every session and 2,530 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens