CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kiro-verify-completion

Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, terse instruction skill whose gate workflow embodies exactly the validation discipline it prescribes, with concrete enums and a copy-paste output template. The main defects are a dangling spec.json reference and slight duplication between the Gate Function and Stop/Escalate rules.

Suggestions

Remove or resolve the instruction "Use the language specified in `spec.json`" — no spec.json exists in the skill bundle, so the line is unactionable and lowers both actionability and conciseness.

Deduplicate the scope-mismatch rule: Gate Function step 5 ("Reject claims that are broader than the evidence") and the NOT_VERIFIED bullet ("The claim exceeds the evidence") state the same rule twice; keep it in one place and cross-reference from the other.

Consider moving the Claim-Specific Rules detail into a short reference file (or trimming it into the gate steps) so the ~126-line body stays a lean overview, strengthening progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no concept re-teaching, terse sections, and a high-value "Common Rationalizations" table. It is not a 5 because there is mild redundancy — "Reject claims that are broader than the evidence" (Gate Function step 5) restates "The claim exceeds the evidence" (Stop / Escalate) — and the dangling "Use the language specified in `spec.json`" line adds a token that earns no place.

4 / 5

Actionability

Guidance is mostly executable: exact claim-type enums (TASK/FIX/TEST_OR_BUILD/FEATURE_GO), a verbatim "Output Format" template, and per-claim-type requirement checklists. It falls short of fully copy-paste-ready anchor 5 because "Use the language specified in `spec.json`" references a file that does not exist in the skill, an instruction the executor cannot resolve.

4 / 5

Workflow Clarity

The "Gate Function" is a numbered 7-step sequence with explicit validation checkpoints (fresh evidence, exit codes, failure counts, skipped scope), a rejection rule for scope mismatch, and explicit escalation (MANUAL_VERIFY_REQUIRED), while "Stop / Escalate" defines error-recovery outcomes for each failure mode. This matches the anchor for a clear sequence with explicit validation steps and feedback loops for error recovery.

5 / 5

Progressive Disclosure

The single file is well-organized with clear section headers, logical ordering, and no nested references, and no bundle files exist to misstructure. It does not earn 5: at ~126 lines it exceeds the under-50-line simple-skill case where sections alone suffice, and "spec.json" is a referenced path with no corresponding file — a minor navigation defect consistent with anchor 4's minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill does and exactly when to use it, with natural trigger phrases covering the main claim types. Its only weaknesses are a single verify action rather than multiple enumerated capabilities and minor trigger overlap with test-running skills.

DimensionReasoningScore

Specificity

The description names its domain ("completion and success claims") and one concrete action ("Verify ... with fresh evidence"), which matches the anchor for 1-2 concrete actions without comprehensive coverage. It does not list several distinct actions the way anchor 4 requires (e.g., extract/fill/merge/convert), so it fits anchor 3 rather than 4 and is clearly above anchor 2's domain-only vagueness.

3 / 5

Completeness

It explicitly answers both questions: "Verify completion and success claims with fresh evidence" (what) and "Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO" (when), with concrete trigger phrases. This mirrors the anchor-5 example structure of a clear what-plus-when pairing; it is well above anchor 4, where the 'when' clause is only generic.

5 / 5

Trigger Term Quality

Phrases like "task is complete", "a fix works", "tests pass", and "feature is ready for GO" are natural things a user or agent would say when needing this skill, giving good keyword coverage. A few natural synonyms (e.g., "done", "finished", "shipped") are missing, which keeps it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The verification-gating niche (fresh evidence, claim scope matching, GO decisions) is distinct, and its triggers ("before claiming ... complete", "ready for GO") would not plausibly route users to unrelated skills. It is not a 5 because "tests pass" as a trigger carries minor overlap risk with closely related test-running/review skills, fitting anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

gotalab/cc-sdd

Path

tools/cc-sdd/templates/agents/claude-code-skills/skills/kiro-verify-completion/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.