New: 98,000+ 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

PUA High-Agency Mode for Pi

by tanweai in tanweai/pua

Pushes an agent that keeps failing, gives up or claims unverified success into a diagnosis, evidence and verification loop, with a Pi extension for persistent mode.

MITAuto-check passedAgent Workflows

Install PUA High-Agency Mode for Pi

skills CLI
$ npx skills add tanweai/pua --skill pua -a claude-code

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

GitHub CLI
$ gh skill install tanweai/pua pua --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/tanweai/pua.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pi/package/skills/pua .claude/skills/pua && 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
pua
GitHub stars
20k
Token cost
~569 tokens
SKILL.md length
253 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Pushes an agent that keeps failing, gives up or claims unverified success into a diagnosis, evidence and verification loop, with a Pi extension for persistent mode.

  • Works in 6 steps: Start with [PUA-DIAGNOSIS] Problem /… → Form 2-3 mutually exclusive hypotheses. → Take the smallest verifiable action. → …
  • Pushing an agent that keeps failing on the same path to change strategy
  • SKILL.md covers When to use, Governance boundary, Required loop and Cultural narratives as…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Aimed at the Pi agent, this skill is the instruction layer of the @tanweai/pi-pua package, which also ships an extension adding /pua-on, /pua-off, /pua-status and /pua-reset commands. It applies only when you explicitly ask for PUA, PIP or try-harder mode, after repeated failures, when the agent turns passive or is about to give up, or when completion is claimed without verification.

The required loop opens with a diagnosis line, forms two or three mutually exclusive hypotheses, takes the smallest verifiable action, runs real checks, switches to a materially different strategy after two failures on one path, and delivers only with evidence and residual-risk accounting. A governance table keeps action, self-review, scoring and environment changes separate, forbids editing tests, graders, CI or permission policy to fake success, and asks before destructive changes. Pressure is directed inward and messages to you stay concise and respectful.

When your agent uses it

  • Pushing an agent that keeps failing on the same path to change strategy
  • Stopping an agent from declaring a task done without running any checks
  • Switching on persistent high-diligence mode in Pi

Example prompts

  • “The build has failed three times in a row. Use the pua skill and diagnose it properly.”
  • “Turn on /pua-on for the rest of this session.”
  • “Stop guessing and give me evidence that the migration really passed.”

Requirements

  • Pi agent with the @tanweai/pi-pua package for the slash commands
  • Compatibility (from SKILL.md): Pi Agent Skills standard; package also ships an extension at ./extensions/pua/index.ts.

Workflow steps

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

  1. Start with [PUA-DIAGNOSIS] Problem / evidence / next action.
  2. Form 2-3 mutually exclusive hypotheses.
  3. Take the smallest verifiable action.
  4. Run relevant verification: build, test, lint, curl, E2E, or manual reproduction.
  5. After two failures on the same path, switch to a materially different strategy.
  6. Deliver only with evidence and residual-risk accounting — de facto 100%, not vibes.

What it can do on your machine

Read from SKILL.md and the folder at commit e6e6cd2. 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.

  • Compatibility

    Pi Agent Skills standard; package also ships an extension at ./extensions/pua/index.ts.

    From compatibility in the SKILL.md frontmatter.

Context cost

PUA High-Agency Mode for Pi loads about 569 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 253 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~569

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 tanweai/pua at commit e6e6cd2, republished under its MIT licence (© tanweai). 253 words, ~569 tokens.

Download SKILL.mdSave it as .claude/skills/pua/SKILL.md (or your agent's skills folder).
name
pua
description
Pi-compatible PUA high-agency governance skill. Use for explicit PUA/PIP requests, repeated failures, passive/giving-up behavior, user frustration, or unverified completion. Pair with /pua-on extension command when persistent pressure is desired.
compatibility
Pi Agent Skills standard; package also ships an extension at ./extensions/pua/index.ts.
license
MIT

PUA for Pi — Skill + Extension Contract

This skill is the instruction layer of @tanweai/pi-pua. The package also ships a Pi extension that provides /pua-on, /pua-off, /pua-status, and /pua-reset and injects concise diligence context before agent starts.

When to use

Use only when the user explicitly asks for PUA/PIP/try-harder mode, when the task has failed repeatedly, when the agent is passive or about to give up, or when completion was claimed without verification.

Governance boundary

Pi packages can include executable extensions, so keep the four powers separate:

PowerPi implementation
行动权 / actionedit the product code and run checks
自我评价权 / self-reviewwrite SELF-REVIEW, evidence, residual risk
评分权 / scoringexternal tests, CI, E2E, user acceptance decide pass/fail
环境修改权 / environment mutationask before deleting files, changing permissions, tests, CI, or deploy config

Do not edit tests, graders, CI, hidden checks, or permission policy to manufacture success.

Required loop

  1. Start with [PUA-DIAGNOSIS] Problem / evidence / next action.
  2. Form 2-3 mutually exclusive hypotheses.
  3. Take the smallest verifiable action.
  4. Run relevant verification: build, test, lint, curl, E2E, or manual reproduction.
  5. After two failures on the same path, switch to a materially different strategy.
  6. Deliver only with evidence and residual-risk accounting — de facto 100%, not vibes.

Cultural narratives as execution modes

  • Alibaba: close target → process → result.
  • Huawei: RCA, self-critique, red-team the fix.
  • ByteDance: optimize for shortest feedback and data.
  • Tencent: race multiple approaches.
  • Musk: question, delete, simplify, accelerate, automate.
  • Jobs: subtract first; make one owner accountable.

Pressure goes inward. User communication stays concise and respectful.

© tanweai, MIT. 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 pi/package/skills/pua of tanweai/pua.

Open the folder on GitHubat commit e6e6cd2

Compare with similar skills

PUA High-Agency Mode for Pi 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.

PUA High-Agency Mode for Pi compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PUA High-Agency Mode for Pi this skilltanweai/pua20k—~569Automated safety check: PassMIT
Verification Before Completionforyourhealth111-pixel/Vibe-Skills3.6k—~1.1kAutomated safety check: PassApache-2.0
Octocode Code Researchbgauryy/octocode949—~1.5kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Orca Run Replayiflytek/skillhub5.2k4 repos~3kAutomated safety check: PassApache-2.0
LoopX Self Repairloopx-project/loopx6.2k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Verification Before Completion

    foryourhealth111-pixel/Vibe-Skills

    Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.

    3.6k GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    949 GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Diagnosing Superpowers Sessions

    obra/superpowers

    Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed

  • Orca Run Replay

    iflytek/skillhub

    Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

    5.2k GitHub starsUsed in 4 repos~3k tokens
    Agent WorkflowsAuto-check passed

  • LoopX Self Repair

    loopx-project/loopx

    Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

    6.2k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Analyze Trajectory

    yologdev/yoyo-evolve

    Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

    1.9k GitHub stars~3.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from tanweai/pua

All 28 skills in this repo

  • Ding Workplace Reminders

    tanweai/pua

    Adds short, pointed workplace reminders drawn from two Chinese essays on corporate culture, nudging the agent to prove results with evidence instead of polished reports.

    20k GitHub stars~556 tokensUpdated 1 mo ago
    Auto-check passed

  • AI Performance Improvement Plan

    tanweai/pua

    Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

    20k GitHub starsUsed in 2 repos~6.9k tokens
    Auto-check passed

  • PUA High-Agency Governance

    tanweai/pua

    Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.

    20k GitHub stars~502 tokensUpdated 1 mo ago
    Auto-check passed

  • PUA Loop

    tanweai/pua

    Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

    20k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • PUA Persistence Engine

    tanweai/pua

    Pushes an agent that keeps failing or gives up to exhaust every option, using harsh corporate-pressure wording, a diagnosis line and a proactivity checklist.

    20k GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed

  • PUA High-Agency Governance for Trae

    tanweai/pua

    An instruction-only discipline for Trae that forces evidence-based work when an agent keeps failing, gives up or declares a task finished without proof.

    20k GitHub stars~878 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about PUA High-Agency Mode for Pi

What does PUA High-Agency Mode for Pi do?

Pushes an agent that keeps failing, gives up or claims unverified success into a diagnosis, evidence and verification loop, with a Pi extension for persistent mode. Aimed at the Pi agent, this skill is the instruction layer of the @tanweai/pi-pua package, which also ships an extension adding /pua-on, /pua-off, /pua-status and /pua-reset commands. It applies only when you explicitly ask for PUA, PIP or try-harder mode, after repeated failures, when the agent turns passive or is about to give up, or when completion is claimed without verification.

When should I use PUA High-Agency Mode for Pi?

PUA High-Agency Mode for Pi fits situations like: pushing an agent that keeps failing on the same path to change strategy; stopping an agent from declaring a task done without running any checks; switching on persistent high-diligence mode in Pi.

How do I install PUA High-Agency Mode for Pi in Claude Code?

Run `npx skills add tanweai/pua --skill pua -a claude-code`. Or copy the skill folder (pi/package/skills/pua in tanweai/pua) into .claude/skills/pua in your project. Claude Code loads it when a task matches its description.

How do I install PUA High-Agency Mode for Pi in Codex?

Run `npx skills add tanweai/pua --skill pua -a codex`. Or copy the skill folder (pi/package/skills/pua in tanweai/pua) into .agents/skills/pua in your project. Codex loads it when a task matches its description.

Can I use PUA High-Agency Mode for Pi 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 tanweai/pua --skill pua -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pua, .gemini/skills/pua, .github/skills/pua and .opencode/skills/pua in your project.

What does PUA High-Agency Mode for Pi need to run?

SKILL.md names no scripts, command-line tools or credentials: PUA High-Agency Mode for Pi is instructions for the agent only. Our summary lists: Pi agent with the @tanweai/pi-pua package for the slash commands. Compatibility (from SKILL.md): Pi Agent Skills standard; package also ships an extension at ./extensions/pua/index.ts..

Does PUA High-Agency Mode for Pi 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 PUA High-Agency Mode for Pi 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 PUA High-Agency Mode for Pi use?

PUA High-Agency Mode for Pi is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PUA High-Agency Mode for Pi use?

About 569 tokens (SKILL.md is roughly 2.3k 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 PUA High-Agency Mode for Pi?

Skills that share tags, products or a category with PUA High-Agency Mode for Pi: Verification Before Completion (foryourhealth111-pixel/Vibe-Skills, 3.6k stars), Octocode Code Research (bgauryy/octocode, 949 stars), Diagnosing Superpowers Sessions (obra/superpowers, 297k stars) and Orca Run Replay (iflytek/skillhub, 5.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PUA High-Agency Mode for Pi?

tanweai (a GitHub user) maintains it in tanweai/pua, which has 19,706 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 9, 2026.

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