recursive-thinking SKILL.md skillA
recursive-thinking from n-n-code/n-n-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add n-n-code/n-n-code-skills/recursive-thinking@git:20260818.1d7259ePins git:20260818.1d7259e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- n-n-code/n-n-code-skills
- Path
.agents/skills/recursive-thinking/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260818.1d7259e, committed Aug 18, 2026
- First version recorded
- Apr 1, 2026
- Size
- 4,891 bytes
- Repository stars
- 4
- License
- MIT
Adversarial review workflow for pressure-testing an existing candidate plan, diagnosis, design, argument, proposal, or recommendation. Use when the user asks to challenge its assumptions, run a premortem, play devil's advocate, red-team a non-security decision, or identify what would change the conclusion. Do not use for open-ended exploration (use thinking) or exploit-focused security review (use security as primary).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Recursive Thinking Challenge an existing candidate hard enough to improve, qualify, or reject it before action. Use this as an orthogonal workflow skill alongside the relevant domain or repository skills. It can be invoked directly whenever a candidate exists; a prior **thinking** pass is not required. If no candidate exists, use **thinking** to frame the decision first. This workflow produces a concise, evidence-based audit trail. It does not require a step-by-step reasoning transcript. ## Routing boundaries - Use **security** as primary when red-teaming means exploit discovery, abuse paths, authentication, authorization, secrets, or trust boundaries. - Use **tester-mindset** as primary when the main artifact is a test strategy, oracle, or edge-case inventory. - Keep language, backend, UI, documentation, prompt, and story skills primary for reviews of their artifacts; add this workflow only when adversarial pressure-testing is materially useful. - Do not use this for simple lookups, routine execution, or open-ended idea generation. ## Optional `n` …
Read the whole file at its exact version.
How to install
mdr add n-n-code/n-n-code-skills/recursive-thinking@sha256:efe64c11cd409458The line at the top of this page pins the label git:20260818.1d7259e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_zrhmc4huh4nuzrvb)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Apr 1, 2026 and Aug 18, 2026, about one every 46 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260818.1d7259e latest | 2026-08-18 | 1d7259e | 4,891 B | A | view · diff |
| git:20260423.b0aeb97 | 2026-04-23 | b0aeb97 | 6,891 B | A | view · diff |
| git:20260401.57655a4 | 2026-04-01 | 57655a4 | 6,903 B | A | view · diff |
| git:20260401.b666e02 | 2026-04-01 | b666e02 | 8,067 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4891 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
n-n-code/n-n-code-skills · 4 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zrhmc4huh4nuzrvb GET https://markdownregistry.com/api/v1/resolve?ref=n-n-code/n-n-code-skills/recursive-thinking GET https://markdownregistry.com/api/v1/blob/efe64c11cd4094588759203652cf8cd03ce140770d4446fcad9314fb04090c3d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.