Agent skill

Instinct Review

by softspark in softspark/ai-toolkit

Reviews/promotes/removes instincts from .claude/instincts/.md.

Apache-2.0Auto-check: notes

Install Instinct Review

skills CLI
$ npx skills add softspark/ai-toolkit --skill instinct-review -a claude-code

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

GitHub CLI
$ gh skill install softspark/ai-toolkit instinct-review --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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/instinct-review .claude/skills/instinct-review && 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
instinct-review
GitHub stars
179
Token cost
~1.2k tokens
SKILL.md length
549 words
Files
1
Skills in repo
112
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reviews/promotes/removes instincts from .claude/instincts/.md.

  • Works in 4 steps: Authoring: Instinct files are written by… → Storage: .claude/instincts/.md, each… → Loading: At session start,… → …
  • SKILL.md covers What This Does, Commands, How Instincts Work and Instinct Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Instinct Review is an agent skill from softspark/ai-toolkit. Reviews/promotes/removes instincts from .claude/instincts/.md. Triggers: instinct review, curate instincts, manage instincts, promote instinct.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

Example prompts

  • “/instinct-review”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Write, Glob

Workflow steps

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

  1. Authoring: Instinct files are written by hand — one markdown file per pattern in .claude/instincts/. There is no automatic session-end…
  2. Storage: .claude/instincts/.md, each carrying a confidence score (see format below).
  3. Loading: At session start, session-start.sh loads every instinct file into context whenever any exist. No instincts on disk means nothing…
  4. Curation: Use /instinct-review to list, promote, remove, or clear them.

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Instinct Review loads about 1.2k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 549 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Glob

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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 549 words, ~1,170 tokens.

Download SKILL.mdSave it as .claude/skills/instinct-review/SKILL.md (or your agent's skills folder).
name
instinct-review
description
Reviews/promotes/removes instincts from `.claude/instincts/*.md`. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
allowed-tools
Bash, Read, Write, Glob
effort
low
user-invocable
true
argument-hint
[--list | --promote <id> | --remove <id> | --clear]

/instinct-review - Manage Learned Instincts

$ARGUMENTS

What This Does

Manages the instinct system: project-local behavioral notes that Claude loads at the start of a session.

Instincts are markdown files in .claude/instincts/, loaded at session start by session-start.sh whenever any exist (set AI_TOOLKIT_HOOK_QUIET=1 to suppress).

Commands

List all instincts
/instinct-review --list

Shows all instincts with confidence scores and source sessions.

Review and curate
/instinct-review

Interactive review: shows each instinct and asks promote/remove/keep.

Promote instinct (always apply)
/instinct-review --promote <filename>
Remove instinct
/instinct-review --remove <filename>
Clear all instincts
/instinct-review --clear

How Instincts Work

  1. Authoring: Instinct files are written by hand — one markdown file per pattern in .claude/instincts/. There is no automatic session-end extractor today (see When NOT to Use).
  2. Storage: .claude/instincts/<pattern-name>.md, each carrying a confidence score (see format below).
  3. Loading: At session start, session-start.sh loads every instinct file into context whenever any exist. No instincts on disk means nothing is loaded; set AI_TOOLKIT_HOOK_QUIET=1 to suppress.
  4. Curation: Use /instinct-review to list, promote, remove, or clear them.

Instinct Format

markdown
# Pattern: [pattern name]
Confidence: 0.85
Sessions: 3
Last seen: 2026-03-25

[Description of the pattern or preference]

Steps

  1. Run ls .claude/instincts/ 2>/dev/null || echo "No instincts yet"
  2. For each instinct file, read it and display confidence/summary
  3. Based on $ARGUMENTS:
    • --list: display table of all instincts
    • --promote <id>: set confidence to 1.0, add "pinned" tag
    • --remove <id>: delete the file
    • --clear: delete all files in .claude/instincts/
    • no args: interactive review of each instinct
  4. Report summary of changes made

Rules

  • MUST list instincts with their source (session ID or date) so the user can judge provenance — anonymous instincts cannot be curated
  • MUST confirm before --clear — this action is irreversible without a backup
  • NEVER invent or edit instinct content — this skill curates existing files, it does not generate new ones
  • NEVER promote an instinct with confidence < 0.7 without explicit user approval — low-confidence patterns are often one-off noise
  • CRITICAL: the user owns the instinct list. Propose changes in interactive mode; apply silently only for explicit --promote, --remove, --clear flags.
  • MANDATORY: after any destructive operation, print the deleted or modified filenames so the user has an audit trail
Show full SKILL.md (223 more words)Show less

Gotchas

  • Instincts live in project-local .claude/instincts/, not in ~/.softspark/ai-toolkit/. Running this skill in a different project sees a different set — do not treat the list as global state.
  • Every instinct file loads into session context by default (whenever the directory is non-empty), so each one costs startup tokens. This is why curation matters — prune aggressively and keep the set small.
  • Promoted instincts (confidence = 1.0) load into every session's context, costing tokens. Too many pinned instincts bloat startup. Keep ≤10 pinned.
  • Instinct files are plain markdown following the format above. If you accumulate many, a --clear and re-author is often cleaner than migrating stale notes after a major toolkit bump.
  • The filename (<pattern-name>.md) is the identity used by --promote and --remove. Renaming files manually breaks those flags until the user reopens the review UI.

When NOT to Use

  • To auto-extract instincts from a session — not implemented. No Stop hook writes instinct files; author them by hand (or via a future extraction tool). This skill curates existing files, it does not generate them.
  • To search past session memory — use /mem-search
  • To edit global toolkit memory files — those live in ~/.claude/projects/*/memory/ and are managed by the auto-memory system, not this skill
  • To stop instincts from loading — delete the files with --clear, or set AI_TOOLKIT_HOOK_QUIET=1 to suppress all session-start output. There is no extraction process to disable.

© softspark, 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

Just SKILL.md in app/skills/instinct-review of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b

Compare with similar skills

Instinct Review 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.

Instinct Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Instinct Review this skillsoftspark/ai-toolkit179—~1.2kAutomated safety check: NotesApache-2.0
Promotealirezarezvani/claude-skills28k2 repos~1.1kAutomated safety check: PassMIT
Checkpoint Promotionwshobson/agents40k—~2kAutomated safety check: PassMIT
Dead Code Removercode-yeongyu/oh-my-openagent70k1 repos~1.8kAutomated safety check: PassCustom licence
Warp Feature Flag Promotionwarpdotdev/warp65k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Remove Bg AutomationComposioHQ/awesome-claude-skills77k3 repos~738Automated safety check: PassNone

Similar skills

  • Promote

    alirezarezvani/claude-skills

    Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

    28k GitHub starsUsed in 2 repos~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Checkpoint Promotion

    wshobson/agents

    Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion.

    40k GitHub stars~2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Dead Code Remover

    code-yeongyu/oh-my-openagent

    Finds unused code in a TypeScript project, confirms each candidate has no references through the language server, then hands removals to parallel agents.

    70k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Walks through promoting a feature-flagged Warp feature to Dogfood, Preview or Stable, including the compile-time bridge and a safe delay before flag cleanup.

    65k GitHub starsUsed in 1 repo~1.1k tokens
    DevelopmentAuto-check passed
  • Remove Bg Automation

    ComposioHQ/awesome-claude-skills

    Automate Remove Bg tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~738 tokens
    Productivity & AutomationAuto-check passed
  • Remove AI Slops

    code-yeongyu/oh-my-openagent

    Removes AI-generated code smells from branch changes or an explicit file list behind regression tests.

    70k GitHub stars~5.3k tokensUpdated today
    Testing & QAAuto-check passed

More from softspark/ai-toolkit

All 112 skills in this repo
  • Prepare Test Env

    softspark/ai-toolkit

    Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.

    179 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes
  • A11y Validate

    softspark/ai-toolkit

    Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~3.8k tokensUpdated yesterday
    Auto-check: notes
  • Analyze

    softspark/ai-toolkit

    Analyzes code quality, complexity, patterns across codebase.

    179 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Autonomous Dev

    softspark/ai-toolkit

    Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.

    179 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes
  • Brand Voice

    softspark/ai-toolkit

    Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • CI

    softspark/ai-toolkit

    Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).

    179 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

Questions about Instinct Review

What does Instinct Review do?

Reviews/promotes/removes instincts from .claude/instincts/.md. Instinct Review is an agent skill from softspark/ai-toolkit.md.

How do I install Instinct Review in Claude Code?

Run `npx skills add softspark/ai-toolkit --skill instinct-review -a claude-code`. Or copy the skill folder (app/skills/instinct-review in softspark/ai-toolkit) into .claude/skills/instinct-review in your project. Claude Code loads it when a task matches its description.

How do I install Instinct Review in Codex?

Run `npx skills add softspark/ai-toolkit --skill instinct-review -a codex`. Or copy the skill folder (app/skills/instinct-review in softspark/ai-toolkit) into .agents/skills/instinct-review in your project. Codex loads it when a task matches its description.

Can I use Instinct Review 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 softspark/ai-toolkit --skill instinct-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/instinct-review, .gemini/skills/instinct-review, .github/skills/instinct-review and .opencode/skills/instinct-review in your project.

What does Instinct Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Instinct Review is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob.

Does Instinct Review 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 Instinct Review safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Instinct Review use?

Instinct Review 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 Instinct Review use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Instinct Review?

Skills that share tags, products or a category with Instinct Review: Promote (alirezarezvani/claude-skills, 28k stars), Checkpoint Promotion (wshobson/agents, 40k stars), Dead Code Remover (code-yeongyu/oh-my-openagent, 70k stars) and Warp Feature Flag Promotion (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Instinct Review?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

Source: softspark/ai-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.