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/decroche-mcp

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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/casius999/decroche-mcp/decroche"><img src="https://agentmods.dev/badge/skills/casius999/decroche-mcp/decroche.svg" alt="Reviewed on agentmods" width="80" 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 5.5	$0.00126	$0.01012
Sonnet 5.5	$0.00063	$0.00506
Haiku 4.5	$0.00031	$0.00253

Measured 2mo ago against content hash cec5f9b1043a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

2mo 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 3mo ago), licensed MIT. It adds 314 tokens to every session and 2,530 once invoked, about $0.0013 per session on Opus 5.5. 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

decroche next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
decrocheCasius999/decroche-mcp	Skill	0	3mo ago	MIT	A	314	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code