CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sce-next-task

Review, approve, implement, verify, and synchronize one SCE plan task

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/sce-next-task/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

The body is a well-engineered orchestration document: fully specified control flow with concrete inputs, branch tables, stops, and failure handling, supported by a clean one-level-deep reference structure that keeps each phase's detail out of context until needed. Its only weakness is mild repetition of the data-preservation and lifecycle-write rules across steps.

DimensionReasoningScore

Conciseness

Dense imperative control flow with zero concept explanations — every line instructs. Minor trimming is possible: the "do not restate, summarize, or reconstruct" family appears three times (step 1's ready branch, step 1's sync_debt handoff, step 3) and the lifecycle-write instruction is duplicated between step 1's sync_debt branch and step 3. Anchor 4 (efficient, minor over-explanation) fits; not 5 because of that repetition, not 3 because nothing is padded.

4 / 5

Actionability

For an instruction-only orchestration skill the guidance is fully actionable: an explicit input grammar with token-matching rules, a concrete example invocation ("$sce-next-task my-plan T03 approved"), exact branch tables on every status value, and runnable emitted commands like "/next-task {plan-path} {task-id}". Anchor 5's copy-paste-ready specific examples covering the common case is the exact fit.

5 / 5

Workflow Clarity

Four numbered steps each dispatch to a named phase with explicit branch-on-status logic, defined stops, and validation feedback loops ("If that lifecycle write fails, treat the outcome as blocked" plus the unrecognized-token error path). This matches anchor 5: clear sequence, explicit validation, error-recovery loops.

5 / 5

Progressive Disclosure

A step-to-reference table maps each step to a real file in references/ (all verified to exist), one level deep, with explicit read-only-what-you-need guidance ("a run that stops at step 1 never needs the other two"). Control flow stays in the body while phase detail is split into the reference files — anchor 5's clear overview with well-signaled one-level-deep references.

5 / 5

Total

19

/

20

Passed

Description

58%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.

The description states a clear, verb-driven "what" with a bounded scope, but omits any "when to use this" guidance and lacks the natural trigger phrases a user would say when needing it. Adding an explicit "Use when..." clause with concrete trigger terms would address the two lowest dimensions at once.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to start, continue, or approve the next task in an SCE plan."

Include natural trigger phrases users would actually say — "next task", "continue the plan", "run task T03" — instead of only the project term "SCE plan task".

Give the key verbs objects to raise specificity, e.g. "Reviews the task's plan entry, implements it, verifies it, and synchronizes plan context".

DimensionReasoningScore

Specificity

Lists five named actions ("Review, approve, implement, verify, and synchronize") bounded by "one SCE plan task", matching anchor 4's several-specific-actions coverage. It falls short of anchor 5 because the verbs lack objects — what is reviewed or verified is never stated.

4 / 5

Completeness

The "what" is explicit ("Review, approve, implement, verify, and synchronize one SCE plan task") but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not anchor 2, because the "what" is clear rather than vague.

3 / 5

Trigger Term Quality

"SCE plan task" supplies the domain keywords "plan" and "task", but the natural phrases a user would actually say ("next task", "continue the plan", "run task T03") are missing and "SCE" is project jargon. This matches anchor 3 — some relevant keywords, missing common variations — rather than anchor 4's good natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

"one SCE plan task" carves a narrow niche, but the generic verb list (review, approve, implement) overlaps with closely related sibling SCE workflow skills referenced in the body. Anchor 4 (mostly distinct, minor overlap risk) fits better than anchor 3, whose example is far broader than this scope.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

crocoder-dev/shared-context-engineering

Path

.agents/skills/sce-next-task/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.