ワンクリックでManusで任意のスキルを実行

report-tool-friction

スター0

フォーク0

更新日2026年6月10日 19:17

This skill should be used whenever a PulseEngine tool (rivet, spar, witness, sigil, meld, loom, synth, kiln, gale, scry, smithy, thrum, temper, mcp — the roster lives in the pulseengine-toolchain memory) produces friction during real work — it errors, crashes, produces wrong or surprising output, is missing a capability you needed, has confusing/undocumented behavior, or forced you into a workaround. ALWAYS use this skill the moment you notice yourself working *around* a tool instead of *with* it, or saying "this should just work but doesn't." The friction is the signal; capturing it as an issue in the tool's own repo is the action. Fires inside [`pulseengine-feature-loop`] and [`release-execution`] and any standalone tool use.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

pulseengine

pulseengine/pulseengine.eu

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Report tool friction

When this fires

You are using a PulseEngine tool to get real work done — not testing the tool, just using it — and it gets in your way. Concretely, any of:

It errors, panics, or crashes on input that should be valid.
It produces wrong, surprising, or unexplained output.
It's missing a capability the task needed, so you reached for something else.
Its behavior was confusing or undocumented enough that you had to guess.
You wrote a workaround — a manual step, a shim, a || true, a hand-edit of generated output, a "do it outside the tool for now."

The moment you notice the workaround is the trigger. A workaround you don't report is friction the next person re-hits. Dogfooding only improves the tools if the friction becomes a tracked, fixable artifact.

This is a standing practice woven through all tool use, not a phase. It fires as you work, not at a checkpoint.

Procedure

1. Identify the right repo

File in the tool's own repo (pulseengine/<tool>), not in the consuming project. If rivet misbehaves while you're shipping spar, the issue goes to pulseengine/rivet. If you can't tell which tool owns the friction, file in the one you invoked and cross-link.

2. Search for a duplicate first

gh issue list --repo pulseengine/<tool> --search "<key phrase>" --state all. If an open issue already covers it, add a comment with your fresh repro instead of opening a new one. Label-search for the friction label too.

3. File it automatically, then mention it

Open the issue without pausing the work, then note it in your response to the user (link + one line). Don't batch, don't wait for permission — friction is cheap to capture and expensive to forget. The body, kept short:

**What I was trying to do:** <the real task, one or two sentences>
**Tool + version:** <tool> <version / commit / "source @ <sha>">
**What happened:** <the error / wrong output / missing capability>
**Repro:** <the exact command(s) or input, minimal>
**Workaround used (if any):** <what I did instead, so the next person isn't blocked>
**Impact:** <blocked / slowed / cosmetic — be honest>

Use a consistent label so these are filterable and reviewable as a batch later:

gh issue create --repo pulseengine/<tool> \
  --title "friction: <short description>" \
  --label tool-friction \
  --body-file <body>
# create the label once per repo if missing:
gh label create tool-friction --color fbbf24 --description "Friction hit while using the tool for real work (dogfooding signal)" --force

4. Keep moving

Filing the issue is not a stop point. Note the workaround in the issue, apply it, and continue the task. The issue is the durable record; the work doesn't wait on the fix.

What makes a good friction issue

The real task is in it. "rivet check failed" is noise; "rivet check rejected a valid verifies link between a test and a sec-constraint while shipping spar v0.9" is signal — it tells the maintainer what use-case broke.
Minimal repro. The smallest command/input that reproduces. If you can't minimize quickly, paste what you have and say so.
Honest impact. Cosmetic friction and blocking friction need different triage. Don't inflate; don't omit.
The workaround is recorded. Even a bad workaround is information — it shows what the tool failed to make easy.

Anti-patterns

Silent workarounds. The single failure mode this skill exists to kill. If you worked around a tool and didn't file, the friction is now invisible.
Batching everything to the end of the session. You forget the specifics; repros decay. File when you hit it.
Filing in the consuming repo instead of the tool repo. The fix lives where the tool lives.
Filing without searching for a dupe. Noise erodes the signal of the tool-friction label.
Turning every preference into friction. Friction is "the tool failed at what it's for," not "I'd have designed it differently." Disagreements about design are a different conversation.
Pausing the real work to perfect the issue. Capture, link, continue. A terse-but-real issue beats a polished one you never filed.

Where this composes

[pulseengine-feature-loop] — friction surfaces at every step (spar passes, rivet validate, witness gaps, sigil verify); report it inline as you go.
[release-execution] — the release-tail is where deferred friction tends to accumulate; the traceability completeness gate often surfaces tool gaps. File them rather than carrying them in your head.
[oracle-gate-a-change] — when the oracle itself is the tool that's broken (the check won't run, or runs wrong), that's friction in the verifier — report it; a broken oracle is worse than a missing one.

このリポジトリの他の Skills

同じリポジトリ

oracle-gate-a-change

pulseengine/pulseengine.eu

This skill should be used whenever proposing, designing, landing, or evaluating a consequential change on a PulseEngine project (rivet, spar, witness, sigil, meld, loom, synth, wohl) — including "propose a change", "add a feature", "fix a bug", "is this safe to land", "what verifies this", "what's the gate", "how do we know this is correct", "before merging this", or whenever a code change needs a mechanical check to back it. ALWAYS use this skill before claiming a property holds and before recommending a change be merged.

2026-07-100

release-execution

pulseengine/pulseengine.eu

This skill should be used when cutting, shipping, or finishing a release — including "ship it", "cut a release", "tag this", "release v0.X.Y", "take this to release", "work the PR queue to green", "finish the release tail", "publish", or any end-to-end release work that involves PRs, reviewers, merging, CI, tagging, GitHub Release, and crates.io publish. ALWAYS use this skill when the user authorizes autonomous release work or asks to "go as long as you can" on a release campaign.

2026-07-100

proof-synthesis

pulseengine/pulseengine.eu

This skill should be used when writing, repairing, or strengthening a machine-checked proof, spec, contract, or invariant in ANY PulseEngine verification backend — Verus (SMT/Z3), Rocq/Coq, Lean 4, Dafny, Kani (bounded model checking), or scry (sound abstract interpretation) — and whenever a proof obligation, assertion, or verification job is failing and needs an iterative generate→verify→refine loop. Backend-agnostic by design: the verifier's own output is the oracle, never an LLM's opinion. Fires across gale, scry, the rules_* proof toolchains, and any repo that carries proofs. Use it for the production of proofs; pair it with oracle-gate-a-change (the verifier is the gate) and stpa-audit/feature-loop (which say *what* must be proven).

2026-07-080

claim-verification

pulseengine/pulseengine.eu

This skill should be used whenever writing or editing a README, a badge, a project description, a blog claim, an honesty ledger, a dossier, or ANY document that asserts what the system does, is, or proves — especially verification claims ("formally verified", "proven", "sound", "verified N/N", trusted-base counts). It treats a document's load-bearing claims as requirements that must stay true over time: mark the assertion, bind it to checkable evidence, and gate it so drift fails the build. Use it to author an honest claim, to audit a doc whose claims may have drifted from reality, or to stand up the claim-check gate in a repo. Composes with traceability-audit (requirements↔tests), oracle-gate-a-change (the gate), and clean-room-verification (review the claim cold).

2026-07-080

issue-hunt

pulseengine/pulseengine.eu

This skill should be used to run an incremental bug/feature hunt over a repo's issue tracker — pick up everything NEW since the last pass (new issues and new comments), digest and triage it, work the actionable items through the verification chain, and accumulate toward a feature release. Use it when the user says "hunt the issues", "do a bug/feature hunt", "look into the issues and work them", "loop through the issues", "digest the new issues and comments since last time", or wants a standing loop (via /loop or a scheduled agent) that drives the tracker toward releases. One invocation is one pass; the "since last time" watermark is what makes it a loop rather than a full re-scan. Composes with release-planning (land + ship), the feature loop, and the operating contract.

2026-06-110

pulseengine-feature-loop

pulseengine/pulseengine.eu

This skill should be used when doing a feature end-to-end on a PulseEngine project (rivet, spar, witness, sigil, meld, loom, synth, wohl, kiln) — including "implement a feature", "add a new requirement", "extend the architecture", "write a new pass", "ship a feature end-to-end", "do this properly with traceability", "model-driven implementation", or any feature work that should pass through the full AADL → WIT → typed traceability → oracle-gated code → MC/DC → attestation → verify loop. ALWAYS use this skill when the user authorizes feature work on a PulseEngine project and the work touches more than a single file.

2026-06-110

name	report-tool-friction
description	This skill should be used whenever a PulseEngine tool (rivet, spar, witness, sigil, meld, loom, synth, kiln, gale, scry, smithy, thrum, temper, mcp — the roster lives in the pulseengine-toolchain memory) produces friction during real work — it errors, crashes, produces wrong or surprising output, is missing a capability you needed, has confusing/undocumented behavior, or forced you into a workaround. ALWAYS use this skill the moment you notice yourself working around a tool instead of with it, or saying "this should just work but doesn't." The friction is the signal; capturing it as an issue in the tool's own repo is the action. Fires inside [`pulseengine-feature-loop`] and [`release-execution`] and any standalone tool use.
metadata	{"author":"pulseengine.eu","version":"0.1.0"}

Report tool friction

When this fires

You are using a PulseEngine tool to get real work done — not testing the tool, just using it — and it gets in your way. Concretely, any of:

It errors, panics, or crashes on input that should be valid.
It produces wrong, surprising, or unexplained output.
It's missing a capability the task needed, so you reached for something else.
Its behavior was confusing or undocumented enough that you had to guess.
You wrote a workaround — a manual step, a shim, a || true, a hand-edit of generated output, a "do it outside the tool for now."

This is a standing practice woven through all tool use, not a phase. It fires as you work, not at a checkpoint.

Procedure

1. Identify the right repo

2. Search for a duplicate first

3. File it automatically, then mention it

**What I was trying to do:** <the real task, one or two sentences>
**Tool + version:** <tool> <version / commit / "source @ <sha>">
**What happened:** <the error / wrong output / missing capability>
**Repro:** <the exact command(s) or input, minimal>
**Workaround used (if any):** <what I did instead, so the next person isn't blocked>
**Impact:** <blocked / slowed / cosmetic — be honest>

Use a consistent label so these are filterable and reviewable as a batch later:

gh issue create --repo pulseengine/<tool> \
  --title "friction: <short description>" \
  --label tool-friction \
  --body-file <body>
# create the label once per repo if missing:
gh label create tool-friction --color fbbf24 --description "Friction hit while using the tool for real work (dogfooding signal)" --force

4. Keep moving

Filing the issue is not a stop point. Note the workaround in the issue, apply it, and continue the task. The issue is the durable record; the work doesn't wait on the fix.

What makes a good friction issue

The real task is in it. "rivet check failed" is noise; "rivet check rejected a valid verifies link between a test and a sec-constraint while shipping spar v0.9" is signal — it tells the maintainer what use-case broke.
Minimal repro. The smallest command/input that reproduces. If you can't minimize quickly, paste what you have and say so.
Honest impact. Cosmetic friction and blocking friction need different triage. Don't inflate; don't omit.
The workaround is recorded. Even a bad workaround is information — it shows what the tool failed to make easy.

Anti-patterns

Silent workarounds. The single failure mode this skill exists to kill. If you worked around a tool and didn't file, the friction is now invisible.
Batching everything to the end of the session. You forget the specifics; repros decay. File when you hit it.
Filing in the consuming repo instead of the tool repo. The fix lives where the tool lives.
Filing without searching for a dupe. Noise erodes the signal of the tool-friction label.
Turning every preference into friction. Friction is "the tool failed at what it's for," not "I'd have designed it differently." Disagreements about design are a different conversation.
Pausing the real work to perfect the issue. Capture, link, continue. A terse-but-real issue beats a polished one you never filed.

Where this composes

[pulseengine-feature-loop] — friction surfaces at every step (spar passes, rivet validate, witness gaps, sigil verify); report it inline as you go.
[release-execution] — the release-tail is where deferred friction tends to accumulate; the traceability completeness gate often surfaces tool gaps. File them rather than carrying them in your head.
[oracle-gate-a-change] — when the oracle itself is the tool that's broken (the check won't run, or runs wrong), that's friction in the verifier — report it; a broken oracle is worse than a missing one.