Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Goal Verifier — measured AI agent skill | DecimalAI

stijnman/goal-verifier

SkillScore68Maintained

Verifies task completion against stated goals before marking work done. Usew hen the user asks to verify success, confirm completion, or says 'did Iachie ve this'. Runs checks + optional self-refine pass. Triggers: verify goal,con firm success, did I achieve this.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

decimalai skills pull stijnman-goal-verifier

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-goal-verifier/SKILL.md

Raw file: /s/stijnman-goal-verifier/SKILL.md ↗ · machine-readable summary at /s/stijnman-goal-verifier.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

—-13% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-32%	0%
case-03	✗→✓	▲ Improved	-26%	0%
case-05	✗→✓	▲ Improved	800%	0%
case-06	✗→✓	▲ Improved	63%	0%
case-07	✗→✓	▲ Improved	-20%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/goal-verifier/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Goal Verifier

When to Use

User says verify goal or task matches this capability
User says confirm success or task matches this capability
User says did I achieve this or task matches this capability
User says check if done or task matches this capability

Workflow

Restate the original goal in one sentence.
List acceptance criteria (explicit or inferred from conversation).
Check each criterion: pass / fail / partial with evidence.
If any fail, invoke self-refine-loop or report gaps.
Only mark complete when all critical criteria pass.

Integrations

self-refine-loop
auto-tester

Error Handling

| Failure | Response | |---------|----------| | Goal undefined | Ask user to confirm goal before verifying. | | False positive risk | Require evidence (file path, command output, or test result). |

Gotchas

Verification is read-only; do not mutate artifacts during checks.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/goal-verifier would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.