CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-trace-plan

Plan traceable work bullets that connect intent, evidence, acceptance, and proof gaps. Use when an idea or reframe needs decomposition into traceable work units before tracker or slice specification.

Quality

73%

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 ./Plugins/synaipse-harness/skills/sy-trace-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 an efficient, well-structured stage playbook with explicit validation gating, failure routing, and clean one-level-deep references. Its main weakness is actionability: it specifies the artifact's field names and status vocabulary but never shows a concrete example artifact or the exact validation commands to run.

Suggestions

Include a minimal example stage artifact (schema_version, stage, status, evidence_refs, blocked_by, next_stage with real values) so the deliverable format is unambiguous.

Name the actual plugin validation and SDK proof commands (or cite the exact wrapper invocation) instead of the vague "run plugin validation and SDK proof commands from the repository wrapper".

Enumerate this stage's exit criteria inline where the handoff references them, so the gate to tracker-plan is verifiable without opening contract.yaml.

DimensionReasoningScore

Conciseness

The body is terse and directive with no concept explanation or padding — sections like "Record evidence refs and classify each lane as pass, fail, blocked, or not_checked" instruct without over-explaining, matching 'lean and efficient; every token earns its place'.

5 / 5

Actionability

Concrete guidance exists (deliverable fields "schema_version, stage, status, evidence_refs, blocked_by, and next_stage" and the pass/fail/blocked/not_checked lane classification), but key execution details are missing: no example stage artifact, and "run plugin validation and SDK proof commands from the repository wrapper" names no actual command — matching 'some concrete guidance but incomplete' rather than the mostly-executable level-4 anchor.

3 / 5

Workflow Clarity

The five-step procedure is clearly sequenced with an explicit fail-fast validation gate ("stop at the first failed required gate... do not proceed to downstream stages") and failure-mode recovery routing, but the exit criteria the handoff depends on are referenced rather than enumerated, matching 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The body is a short overview with a labeled References section pointing one level deep to contract.yaml, evals.yaml, task-profile.json, and source-context.yaml, all of which exist in references/ — clear split, well-signaled, easy navigation.

5 / 5

Total

17

/

20

Passed

Description

55%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 answers both what and when with an explicit boundary against sibling stages, but its trigger vocabulary is internal pipeline jargon rather than natural user phrasing, and its action coverage is thin. It reads as a stage-routing label more than a user-facing trigger description.

Suggestions

Add natural trigger phrases users would actually say (e.g., "break this idea into work items", "decompose a request into tasks", "plan work bullets") alongside the stage jargon.

Expand the what clause with the concrete outputs the stage produces (e.g., work bullets linking each intent to acceptance criteria and evidence) to lift specificity beyond a single action.

State what distinguishes this from generic task decomposition or planning skills to reduce overlap with broader planning-related skills.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("Plan traceable work bullets that connect intent, evidence, acceptance, and proof gaps") but does not list several specific actions with comprehensive coverage, so it matches the 'names domain and 1-2 concrete actions' anchor rather than the level-4 anchor.

3 / 5

Completeness

Both what ("Plan traceable work bullets that connect intent, evidence, acceptance, and proof gaps") and when ("Use when an idea or reframe needs decomposition...") are explicitly present, but the when clause uses stage jargon rather than concrete trigger phrases a user would actually say, so it falls just below the level-5 anchor.

4 / 5

Trigger Term Quality

Triggers rely on internal Harness jargon ("an idea or reframe needs decomposition into traceable work units before tracker or slice specification") — users would not naturally say "reframe", "traceable work units", or "slice specification"; only the generic word "idea" is natural, matching the 'one or two generic keywords; missing the natural phrases users say' anchor.

2 / 5

Distinctiveness Conflict Risk

The phrase "before tracker or slice specification" explicitly positions the skill against its sibling stages, leaving only minor overlap risk with closely related skills (tracker-plan, sy-reframe) — matching 'mostly distinct; minor overlap risk' rather than the level-3 anchor where boundary positioning is absent.

4 / 5

Total

13

/

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

jscraik/Agent-Skills

Path

Plugins/synaipse-harness/skills/sy-trace-plan/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.