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

Review Input

by digipulse-engineering in digipulse-engineering/GAAI-framework

Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state.

Custom licenceAuto-check passedDevelopment

Install Review Input

skills CLI
$ npx skills add digipulse-engineering/GAAI-framework --skill review-input -a claude-code

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

GitHub CLI
$ gh skill install digipulse-engineering/GAAI-framework review-input --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/digipulse-engineering/GAAI-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.gaai/core/skills/discovery/review-input .claude/skills/review-input && 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
review-input
GitHub stars
163
Token cost
~5.6k tokens
SKILL.md length
1,888 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
Custom licence

At a glance

Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state.

  • Works in 8 steps: Classification (always runs,… → Evaluation (conditional on Phase 1… → 1 — Load domain governance → …
  • Tasks that involve Software architecture
  • SKILL.md covers Purpose, When to Activate, Architecture — Two Phases and Phase 1 — Classification, plus 7 more sections
  • Calls git

What it does

Review Input is an agent skill from digipulse-engineering/GAAI-framework. Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Universal interceptor with domain auto-detection, 2-phase classification + evaluation, and triple-verdict output (veracity / fit / actionability). Anti-girouette guardrail that distinguishes drift from pivot — preserves human decisional authority. Manual invocation only (no hooks, no enforcement). Activate when an input may affect strategic-frame.md, a DEC, an OT, an…

Its SKILL.md is about 5.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Works with any filesystem-based AI coding agent

It sits in Development, covering Software architecture and Deep research. The repository describes itself as: Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until…

When your agent uses it

  • Tasks that involve Software architecture
  • Tasks that involve Deep research

Example prompts

  • “/review-input”

Requirements

  • Compatibility (from SKILL.md): Works with any filesystem-based AI coding agent

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Classification (always runs, deterministic, ~30 seconds)
  2. Evaluation (conditional on Phase 1 verdict)
  3. 1 — Load domain governance
  4. 2 — Veracity Gate (skip if zero factual claim detected)
  5. 3 — Decision Filters check (universal, all domains)
  6. 4 — Triple verdict (the core output — replaces single ACCEPT/REJECT)
  7. 5 — Past↔Present symmetry (mandatory question)
  8. 6 — Falsifiability check

What it can do on your machine

Read from SKILL.md and the folder at commit a26ea7a. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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.

  • Compatibility

    Works with any filesystem-based AI coding agent

    From compatibility in the SKILL.md frontmatter.

Context cost

Review Input loads about 5.6k tokens when it runs. Until then it costs about 158 tokens; SKILL.md has 1,888 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~158
When it runs · the whole SKILL.md, loaded when a task matches
~5.6k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,888 words (~5,585 tokens).

“Intercept ANY input — human or agent — that may mutate persistent project state, BEFORE it becomes a DEC, an OT amendment, a strategic-frame edit, an architectural pattern, or a backlog story scope change. Produce a structured 3-verdict report that…”

— opening of SKILL.md by digipulse-engineering, Custom licence
name
review-input
compatibility
Works with any filesystem-based AI coding agent
license
ELv2
metadata.author
gaai-framework
metadata.version
1.0
metadata.category
discovery
metadata.track
discovery
metadata.id
SKILL-RIN-001
metadata.updated_at
2026-04-27
metadata.status
stable
metadata.tags
review, adversarial, anti-girouette, anti-drift, universal-interceptor, three-verdict, pivot-vs-drift, veracity, governance, decision-filter
inputs
Input text — any origin (human idea, agent proposal, research excerpt, feedback, bug observation, external signal), Optional intent declaration — drift_check…

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .gaai/core/skills/discovery/review-input of digipulse-engineering/GAAI-framework.

Open the folder on GitHubat commit a26ea7a

Compare with similar skills

Review Input 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.

Review Input compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Input this skilldigipulse-engineering/GAAI-framework163—~5.6kAutomated safety check: PassCustom licence
Workflow AuthoringQuintinShaw/pi-dynamic-workflows554—~671Automated safety check: PassMIT
Diagram312362115/claude107—~2.7kAutomated safety check: PassMIT
Plugin Improveglittercowboy/plugin-freedom-system216—~4.2kAutomated safety check: NotesNone
Documentation Research Methodologyprime-radiant-inc/greenfield292—~4.6kAutomated safety check: PassApache-2.0
Asksd0xdev/sd0x-harness192—~2.1kAutomated safety check: NotesMIT

Similar skills

  • Workflow Authoring

    QuintinShaw/pi-dynamic-workflows

    Guidance for writing, editing, reviewing, and debugging JavaScript workflow code for pi-dynamic-workflows.

    554 GitHub stars~671 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Diagram

    312362115/claude

    专业图表生成技能：根据需求自动选择合适的图表类型，生成符合设计规范的 PNG 图表. An agent skill from 312362115/claude.

    107 GitHub stars~2.7k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • Plugin Improve

    glittercowboy/plugin-freedom-system

    Fix bugs, add features to completed plugins. An agent skill from glittercowboy/plugin-freedom-system.

    216 GitHub stars~4.2k tokensUpdated 10 mo ago
    DevelopmentAuto-check: notes

  • Documentation Research Methodology

    prime-radiant-inc/greenfield

    Method for extracting behavioral specifications from a product's public documentation: tiered search order, claim extraction rules, output structure, stop criteria and gap analysis.

    292 GitHub stars~4.6k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

  • Ask

    sd0xdev/sd0x-harness

    Context-aware Q&A with auto context gathering. An agent skill from sd0xdev/sd0x-harness.

    192 GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed

More from digipulse-engineering/GAAI-framework

All 55 skills in this repo

  • Eval Run

    digipulse-engineering/GAAI-framework

    Evaluate any output file against a structured evals.yaml assertions file and produce a score report with per-assertion pass/fail results.

    163 GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed

  • Pattern Transfer

    digipulse-engineering/GAAI-framework

    Discover structurally similar patterns across domains, assess transfer viability via structural invariant checking, and propose domain adaptations with risk gates.

    163 GitHub stars~2.3k tokensUpdated 8 days ago
    Auto-check passed

  • Skill Optimize

    digipulse-engineering/GAAI-framework

    Run a structured evaluate-analyze-improve cycle on any GAAI skill to measure quality, detect regressions, and propose targeted improvements.

    163 GitHub stars~2k tokensUpdated 8 days ago
    Auto-check passed

  • Abort Safe Handler

    digipulse-engineering/GAAI-framework

    Orchestrator-level Stage 4 entry gate for /gaai:bootstrap. An agent skill from digipulse-engineering/GAAI-framework.

    163 GitHub stars~2.6k tokensUpdated 8 days ago
    Auto-check passed

  • Create Skill

    digipulse-engineering/GAAI-framework

    Guide creation of a new GAAI skill following the agentskills.io spec and GAAI best practices.

    163 GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed

  • Discovery High Level Plan

    digipulse-engineering/GAAI-framework

    Transform vague or high-level human intent into a governed Discovery action plan.

    163 GitHub stars~570 tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Review Input

What does Review Input do?

Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Review Input is an agent skill from digipulse-engineering/GAAI-framework. Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state.

When should I use Review Input?

Review Input fits situations like: tasks that involve Software architecture; tasks that involve Deep research.

How do I install Review Input in Claude Code?

Run `npx skills add digipulse-engineering/GAAI-framework --skill review-input -a claude-code`. Or copy the skill folder (.gaai/core/skills/discovery/review-input in digipulse-engineering/GAAI-framework) into .claude/skills/review-input in your project. Claude Code loads it when a task matches its description.

How do I install Review Input in Codex?

Run `npx skills add digipulse-engineering/GAAI-framework --skill review-input -a codex`. Or copy the skill folder (.gaai/core/skills/discovery/review-input in digipulse-engineering/GAAI-framework) into .agents/skills/review-input in your project. Codex loads it when a task matches its description.

Can I use Review Input 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 digipulse-engineering/GAAI-framework --skill review-input -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-input, .gemini/skills/review-input, .github/skills/review-input and .opencode/skills/review-input in your project.

What does Review Input need to run?

Going by SKILL.md and its folder, Review Input needs the command-line tools its instructions call (git). Compatibility (from SKILL.md): Works with any filesystem-based AI coding agent.

Does Review Input access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Review Input 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 Review Input use?

Review Input has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Review Input use?

About 5.6k tokens (SKILL.md is roughly 22k 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 Review Input?

Skills that share tags, products or a category with Review Input: Workflow Authoring (QuintinShaw/pi-dynamic-workflows, 554 stars), Diagram (312362115/claude, 107 stars), Plugin Improve (glittercowboy/plugin-freedom-system, 216 stars) and Documentation Research Methodology (prime-radiant-inc/greenfield, 292 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Input?

digipulse-engineering (a GitHub organization) maintains it in digipulse-engineering/GAAI-framework, which has 163 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 29, 2026.

Source: digipulse-engineering/GAAI-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.