Dev & Engineering workflowverificationtestingsuperpowers

Verification Before Completion

No claim of "done" or "tests pass" without fresh evidence from actually running the check — including hedges like "should" or "looks like"

FollowSkills review · FSRS-1.0
Use with care
67/ 100
Utility17 / 20

The skill addresses a concrete task: verification before claiming completion, committing, or creating a PR. Its evidence-before-assertions principle, gate sequence, and examples for tests, builds, requirements, regression tests, and agent delegation provide strong practical value. Evidence gaps include no explicit boundaries for choosing applicable projects or commands and no complete alternative process when verification cannot run.

Reliability14 / 20

The sequence of identifying a proving command, running the full command, reading output and exit status, and reconciling the result is consistent and oriented toward reproducibility. It also covers regression-test red-green verification and independent checking of agent reports. Evidence gaps include no method for discovering commands and no detailed handling for missing tools, incomplete environments, timeouts, nonzero exits, or ambiguous output; there is also no skill-specific behavioral test evidence.

Safety15 / 25

The skill reduces the risk of false completion claims and unverified commits or PRs, and requires checking the VCS diff after an agent reports success. It requests no credentials, network access, or specific file changes, and shows no malicious or destructive default. Safety remains limited because running a “full command” can cause build, test, commit, or other external side effects; the skill lacks least-privilege guidance, consent gates, sandboxing, sensitive-data handling, failure rollback, and command safety review.

Evidence9 / 15

The skill explicitly requires fresh verification evidence, full-output reading, exit-code checks, and failure counts, while distinguishing claims such as tests passing, builds succeeding, and requirements being met. Evidence gaps are material: the command results in the examples are illustrative text, not execution records available to this static review; the “24 failure memories” statement has no corroboration in the supplied skill; and there is no independent evaluation, test result, or explicit fact-versus-inference labeling for this SKILL.md.

Usability7 / 10

Triggers are clear, and the iron law, gate function, failure list, and common patterns are easy for a coding agent to apply. Evidence gaps include no setup or harness requirements, input/output contract, cost or duration guidance, compatibility details across agent tools, troubleshooting examples, or safe exit/reporting behavior when verification is blocked.

Maintenance5 / 10

The target file has name and description metadata; shared repository material provides limited maintenance context through the MIT license, version 6.1.1, contribution process, issue channel, and update note. The skill itself has no version, changelog, named maintainer, release responsibility, or dedicated update path. Publisher provenance is not verified by the FollowSkills enterprise registry and therefore cannot add governance credit.

Evidence confidence:Low Reviewed Jul 15, 2026 Reviewed revision d884ae04edeb
Before you use it
  • Do not interpret “run the full command” as unconditional permission to execute commands that may commit, delete, deploy, or access external systems; review side effects and obtain consent when needed.
  • If a verification command fails, is unavailable, or produces ambiguous output, do not claim success; report the actual state, blocking reason, and unverified scope.
  • This assessment is static only: the skill, commands, and tests were not executed, and repository test material is not a substitute for skill-specific behavioral evidence.
Review evidence [1][2][3][4][5][6][7]
See the full review method →

What it does & when to use it

The shortest but most uncompromising skill in the set: its core position is that claiming completion without verification is dishonesty, not efficiency. Before making any completion or passing claim, it requires identifying exactly what command would prove the claim, running it right then, reading the full output, and confirming the output actually supports the claim — only then is the conclusion allowed. Getting the order wrong or skipping any step counts as a violation.

Provides a claim → required evidence → insufficient evidence table (e.g. "tests pass" needs a fresh test-command output showing 0 failures — "ran earlier" or "should pass" don't count). Lists a red-flags checklist: hedging language ("should", "probably", "seems to"), expressing satisfaction before verification ("great!", "done!"), and trusting a subagent's own success report without independent verification — all of these mean stop immediately. Gives a concrete red-green verification procedure for regression tests (write the test → run it, passes → revert the fix → run it, must fail → restore the fix → run it, passes again) that proves the test actually detects the original bug, not just that it appears to. For subagent-reported completion specifically, requires checking the actual version-control diff instead of trusting the report text alone.

  1. Before any "tests pass," "bug is fixed," or "build succeeds" claim, run the corresponding command fresh for current-turn evidence rather than relying on memory of a previous run
  2. After a subagent reports "task complete," check its actual committed diff to verify the change instead of taking the report text at face value
  3. After writing a regression test, verify with the red-green cycle that it actually catches the original bug (reverting the fix must make the test fail) rather than assuming it's valid once written

Pros & cons

Pros
  • The claim → evidence → insufficient-evidence table turns "what counts as verified" into a checkable, concrete standard instead of an unenforceable "be careful"
  • Requiring extra verification specifically for subagent success reports targets a real, easily overlooked trust trap
  • The regression-test red-green procedure (reverting the fix must reproduce the failure) is a genuinely useful concrete technique that proves a test is effective rather than just looking like it tests something
Limitations
  • Only reliably self-enforcing on harnesses that actually read and follow SKILL.md instructions (Claude Code, Codex CLI, etc.) — in a plain chat interface it's just a document a human has to apply by hand.
  • Requiring fresh run-evidence for every small conclusion can noticeably slow the feedback loop when verification itself is expensive (a run that takes tens of minutes), which is a real trade-off to weigh
  • Like every other Superpowers skill, a self-imposed rule like this only works if the model actually follows it — there's no external enforcement mechanism

How to install

Installed as part of the obra/superpowers plugin — individual skills can't be installed standalone:

  1. Claude Code: official marketplace /plugin install superpowers@claude-plugins-official; or register the community marketplace with /plugin marketplace add obra/superpowers-marketplace then /plugin install superpowers@superpowers-marketplace
  2. Also supports Antigravity, Codex App/CLI, Cursor, Factory Droid, GitHub Copilot CLI, Kimi Code, OpenCode, and Pi — see the repo README for the exact command per harness

Once installed, this skill activates alongside the other 13 Superpowers skills, auto-triggered by using-superpowers based on context — there's no separate invocation step.

How to use

Triggers automatically before any completion/passing/fixed conclusion, and before committing, pushing, or opening a PR. Also explicitly referenced downstream by subagent-driven-development and systematic-debugging to gate completion claims at each stage.

Compared to similar skills

Compared to no such rule — the model concluding from a previous run or its own judgment — this skill tightly binds "completion claim" to "fresh verification evidence," directly targeting the common agent failure mode of reporting success prematurely. It complements test-driven-development's "write the test first" — one governs how code gets written, the other governs how results get reported.

FAQ

Why can't a subagent's own "success" report be trusted?
The SKILL.md lists trusting a subagent's report as a bad example, requiring the actual version-control diff to be checked instead — report text alone isn't evidence; only checkable output (a diff, test results) counts.

More skills from this repository

All from obra/superpowers

Dev & Engineering

Test-Driven Development (TDD)

Iron rule: no production code without a failing test written first — code written out of order gets deleted and restarted, no "tests added after"

Dev & Engineering

Brainstorming (Requirements & Design)

Forces requirement clarification before any code gets written — hard-blocks implementation until a design is approved

Dev & Engineering

Finishing a Development Branch

Verifies tests pass, then walks you through a fixed merge/PR/keep/discard menu and cleans up worktrees by strict ownership rules

Dev & Engineering

Receiving Code Review

Bans performative agreement like "you're absolutely right!" — requires verifying feedback before implementing or pushing back

Dev & Engineering

Requesting Code Review

Dispatches a reviewer subagent with isolated context to check your changes, instead of self-grading in the same session that wrote them

Dev & Engineering

Systematic Debugging

Requires completing root-cause investigation before proposing any fix — explicitly bans "just try changing this and see"

Dev & Engineering

Writing Plans

Breaks requirements into 2-5-minute tasks an implementer with zero codebase context could follow verbatim — bans placeholders like "TBD" or "fill in details"

Dev & Engineering

Subagent-Driven Development

Dispatches a fresh implementer subagent per task in the same session, with two-stage review and a progress ledger that survives context compaction

Dev & Engineering

Executing Plans

Batch-executes an already-written implementation plan with human checkpoints, for sessions without subagent support

Dev & Engineering

Using Git Worktrees

Prefer the platform's native isolation tool before starting new feature work; fall back to manual git worktrees only when no native tool exists

Dev & Engineering

Dispatching Parallel Agents

Fan out 2+ genuinely independent tasks to parallel subagents in one shot instead of queuing them sequentially

Dev & Engineering

Writing Skills (Authoring & Testing Skills)

Applies TDD's red-green-refactor to writing skill documentation itself — expose real failure modes with a no-skill baseline test first, then write targeted guidance instead of guessing

Dev & Engineering

Using Superpowers (Bootstrap)

The entry-point skill for the whole Superpowers system — mandates invoking a relevant skill whenever there's even a 1% chance it applies

Related skills