New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Recursive Spec

by try-works in try-works/recursive-mode

Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs.

Apache-2.0Auto-check passedDevelopment

Install Recursive Spec

skills CLI
$ npx skills add try-works/recursive-mode --skill recursive-spec -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install try-works/recursive-mode recursive-spec --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/try-works/recursive-mode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recursive-spec .claude/skills/recursive-spec && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recursive-spec
GitHub stars
136
Token cost
~1.4k tokens
SKILL.md length
705 words
Files
3 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs.

  • Works in 3 steps: First ask whether the user wants help… → If the user replies positively, ask:… → Then gather context, read the repo, and…
  • The user wants help creating a plan
  • SKILL.md covers Primary Use Case, Conversation Contract, Draft Handling Before Approval and Required Read Behavior, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recursive Spec is an agent skill from try-works/recursive-mode. Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Use when the user wants help creating a plan, spec, scope, or requirements for work that does not yet have a run, especially prompts like "create a plan", "help me plan", "create a spec", "write requirements", or similar derivatives.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/patterns.md`).

It sits in Development. The repository describes itself as: Recursive workflow for agentic engineering. Like Factory Missions but properly recursive, free and open source. The licence is Apache-2.0.

When your agent uses it

  • The user wants help creating a plan
  • Requirements for work that does not yet have a run
  • Especially prompts like create a plan
  • Write requirements

Example prompts

  • “create a plan”
  • “help me plan”
  • “create a spec”
  • “/recursive-spec”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. First ask whether the user wants help creating a spec for a recursive run.
  2. If the user replies positively, ask: What do you want to do?
  3. Then gather context, read the repo, and co-author the requirements.

What it can do on your machine

Read from SKILL.md and the folder at commit ff75bc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recursive Spec loads about 1.4k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 705 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from try-works/recursive-mode at commit ff75bc7, republished under its Apache-2.0 licence (© try-works). 705 words, ~1,422 tokens.

Download SKILL.mdSave it as .claude/skills/recursive-spec/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
recursive-spec
description
Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Use when the user wants help creating a plan, spec, scope, or requirements for work that does not yet have a run, especially prompts like "create a plan", "help me plan", "create a spec", "write requirements", or similar derivatives.

recursive-spec

Use this skill to co-author a repo-aware 00-requirements.md for a new recursive-mode run.

This skill is for requirements/spec authoring before implementation starts. It does not replace /.recursive/RECURSIVE.md, and it should not skip ahead to Phase 2 planning or Phase 3 implementation.

Primary Use Case

Use recursive-spec when the user wants help shaping work before a run exists, especially with prompts like:

  • create a plan
  • help me plan
  • create a spec
  • write requirements
  • spec this out
  • scope this

The important signal is plan/spec language for a new run, not implementation of an existing run.

Conversation Contract

When the trigger is detected:

  1. First ask whether the user wants help creating a spec for a recursive run.
  2. If the user replies positively, ask: What do you want to do?
  3. Then gather context, read the repo, and co-author the requirements.

Do not jump straight into writing 00-requirements.md before the user confirms they want spec help.

Draft Handling Before Approval

Until the user explicitly approves the spec:

  • keep the draft outside the repository worktree
  • prefer a temporary session artifact or scratch file
  • do not create /.recursive/run/<run-id>/
  • do not write 00-requirements.md

If the user rejects the draft, revise it or discard the temporary draft artifact. Do not leave behind a half-approved run folder.

Required Read Behavior

Before drafting requirements, read:

  1. /.recursive/STATE.md
  2. /.recursive/DECISIONS.md
  3. /.recursive/memory/MEMORY.md
  4. relevant memory shards only when they actually matter
  5. the most relevant code and tests for the requested area

The skill should be repo-aware, not a blind questionnaire. Use the control-plane docs to understand current truth and the codebase to understand actual surfaces, coupled modules, existing tests, and likely boundaries.

Authoring Flow

Use a guided interview. Ask one focused question at a time when the answer is not already grounded by repo docs or code.

Recommended sequence:

  1. Goal and user outcome
  2. Task type: feature, bugfix, refactor, migration, investigation
  3. Affected subsystem or files
  4. In-scope requirements (R#)
  5. Observable acceptance criteria for each requirement
  6. Edge cases, failure paths, and exclusions
  7. Constraints, fixed decisions, and boundaries
  8. Open unknowns that must be resolved before Phase 0 is locked

Prefer proposing draft wording and asking the user to confirm or correct it rather than asking the user to author the whole document from scratch.

Quality Rules

Borrow the strongest authoring ideas from contract-first workflows, but keep the output native to recursive-mode:

  • start with user intent and desired outcome
  • separate fixed decisions from open questions
  • define deterministic, observable acceptance criteria
  • include exception and failure-path thinking instead of only the happy path
  • make boundaries concrete enough to guide later AS-IS analysis and planning
  • keep out-of-scope items explicit

Do not introduce a separate .spec DSL or a second workflow format.

Show full SKILL.md (251 more words)Show less

Output Contract

The finished output should become:

  • /.recursive/run/<run-id>/00-requirements.md

Use the repository's native Phase 0 requirements structure:

  • keep the scaffolded header from recursive-init, including Workflow version: recursive-mode-audit-v2
  • keep the required ## TODO section and replace placeholder checklist items rather than deleting the heading
  • ## Requirements
  • ## Out of Scope
  • ## Constraints

Within ## Requirements, each R# should include:

  • a short title
  • a clear description
  • observable acceptance criteria bullets

Run Creation Rule

Do not create the run folder immediately.

  1. Draft and refine the requirements with the user first.
  2. Keep the draft in a temporary non-repo artifact until approval.
  3. Confirm the user approves the spec and that it is complete enough to proceed.
  4. Create the run with .recursive/scripts/recursive-init.py or .recursive/scripts/recursive-init.ps1.
  5. Replace the scaffolded 00-requirements.md with the approved requirements content.

This keeps the run artifact grounded in user-approved requirements instead of half-formed notes.

Routing Awareness

If spec authoring uses delegated critique, delegated review, or any other external model help to shape the draft, re-read:

  • /.recursive/config/recursive-router.json
  • /.recursive/config/recursive-router-discovered.json

immediately before choosing that CLI/model, and route through recursive-router instead of inventing an ad hoc model choice.

Boundaries

  • Stay focused on 00-requirements.md authoring for a new run.
  • Do not silently convert this into Phase 2 planning.
  • Do not start implementation just because the requirements became clear.
  • Do not skip code reading when repository structure matters to scope or constraints.
  • Do not create a run until the user-approved spec is ready to write.
  • Do not write repository requirements artifacts from an unapproved draft.

References

  • /.recursive/RECURSIVE.md
  • /.recursive/STATE.md
  • /.recursive/DECISIONS.md
  • /.recursive/memory/MEMORY.md
  • ../recursive-mode/references/artifact-template.md
  • ./references/patterns.md

© try-works, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/recursive-spec of try-works/recursive-mode.

  • SKILL.md
  • agents/openai.yaml
  • references/patterns.md

Open the folder on GitHubat commit ff75bc7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in try-works/recursive-mode, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Recursive Spec next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recursive Spec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recursive Spec this skilltry-works/recursive-mode136—~1.4kAutomated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k24 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT

Similar skills

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 24 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 22 repos~577 tokens
    DevelopmentAuto-check passed

More from try-works/recursive-mode

All 9 skills in this repo

  • Recursive Mode

    try-works/recursive-mode

    Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance.

    136 GitHub stars~3.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Recursive Debugging

    try-works/recursive-mode

    A skill your agent uses when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior.

    136 GitHub stars~3.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Recursive Review Bundle

    try-works/recursive-mode

    A skill your agent uses when recursive-mode work needs a canonical delegated-review or audit handoff.

    136 GitHub stars~873 tokensUpdated 2 mo ago
    Auto-check passed

  • Recursive Subagent

    try-works/recursive-mode

    A skill your agent uses when recursive-mode work may benefit from delegated audit, review, or bounded implementation support.

    136 GitHub stars~3k tokensUpdated 2 mo ago
    Auto-check passed

  • Recursive TDD

    try-works/recursive-mode

    A skill your agent uses when implementing any code in recursive-mode Phase 3.

    136 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check passed

  • Recursive Worktree

    try-works/recursive-mode

    A skill your agent uses when starting any recursive-mode requirement to set up an isolated git worktree.

    136 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Recursive Spec

What does Recursive Spec do?

Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Recursive Spec is an agent skill from try-works/recursive-mode. Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs.

When should I use Recursive Spec?

Recursive Spec fits situations like: the user wants help creating a plan; requirements for work that does not yet have a run; especially prompts like create a plan; write requirements.

How do I install Recursive Spec in Claude Code?

Run `npx skills add try-works/recursive-mode --skill recursive-spec -a claude-code`. Or copy the skill folder (skills/recursive-spec in try-works/recursive-mode) into .claude/skills/recursive-spec in your project. Claude Code loads it when a task matches its description.

How do I install Recursive Spec in Codex?

Run `npx skills add try-works/recursive-mode --skill recursive-spec -a codex`. Or copy the skill folder (skills/recursive-spec in try-works/recursive-mode) into .agents/skills/recursive-spec in your project. Codex loads it when a task matches its description.

Can I use Recursive Spec in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add try-works/recursive-mode --skill recursive-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recursive-spec, .gemini/skills/recursive-spec, .github/skills/recursive-spec and .opencode/skills/recursive-spec in your project.

What does Recursive Spec need to run?

SKILL.md names no scripts, command-line tools or credentials: Recursive Spec is instructions for the agent only.

Does Recursive Spec access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Recursive Spec safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recursive Spec use?

Recursive Spec is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recursive Spec use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 979 tokens, read only when the agent opens those files.

What are the alternatives to Recursive Spec?

Skills that share tags, products or a category with Recursive Spec: Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recursive Spec?

try-works (a GitHub user) maintains it in try-works/recursive-mode, which has 136 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on July 24, 2026.

Source: try-works/recursive-mode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.