CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-tracker-plan

Plan tracker-ready slices with dependencies, labels, acceptance fields, and validation placeholders. Use when trace work needs Linear-ready or tracker-ready issue structure without actually mutating the tracker.

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

Quality

Content

67%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 orchestration-style skill body with a clear procedure, fail-fast validation, failure-mode routing, and properly split references. Its main weakness is actionability: the actual planning method for tracker-ready slices is delegated without a concrete example or format.

Suggestions

Add a short example of a tracker-ready slice (e.g. a fenced YAML block showing a slice with its dependencies, labels, acceptance fields, and validation placeholder) so the core deliverable is executable rather than delegated to 'work owned by tracker-plan'.

Replace 'Run the smallest relevant local check' and 'SDK proof commands from the repository wrapper' with the exact commands or a pointer to where they are defined in the stage contract.

Annotate each entry in References with when it is needed (e.g. 'Stage contract: required field definitions — read before emitting the stage result'), and drop the 'When to use' section that repeats the description verbatim.

DimensionReasoningScore

Conciseness

The body is lean with no concept explanations Claude already knows, but "Use when trace work needs Linear-ready or tracker-ready issue structure without actually mutating the tracker" duplicates the description verbatim, and Deliverables overlap the Procedure steps.

4 / 5

Actionability

Concrete elements exist (deliverable field names like schema_version, evidence_refs, blocked_by; status enums pass/fail/blocked/not_checked; named next stage slice-spec), but the core task is reduced to "Perform only the work owned by tracker-plan" with no example slice, format, or method for structuring dependencies, labels, and acceptance fields.

3 / 5

Workflow Clarity

The numbered 5-step procedure with a fail-fast validation gate ("stop at the first failed required gate"), lane classification, and conditional handoff gives a clear sequence with checkpoints, but "smallest relevant local check" and "SDK proof commands from the repository wrapper" leave the actual validation commands unspecified.

4 / 5

Progressive Disclosure

Four clearly labeled one-level-deep references (contract, evals, task profile, source context), all verified to exist in ./references/, keep the body an appropriate overview — though the body gives no guidance on when each reference should be consulted.

4 / 5

Total

15

/

20

Passed

Description

83%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: it states concrete deliverable components, includes an explicit and conditional 'Use when' clause, and bounds the skill's authority (no tracker mutation). Main gaps are the single action verb and a few missing natural trigger phrasings.

DimensionReasoningScore

Specificity

"Plan tracker-ready slices with dependencies, labels, acceptance fields, and validation placeholders" names the domain and several concrete deliverable components, but centers on a single action verb rather than the multiple distinct actions of the 5-anchor.

4 / 5

Completeness

It explicitly answers both what ("Plan tracker-ready slices with dependencies, labels, acceptance fields, and validation placeholders") and when ("Use when trace work needs Linear-ready or tracker-ready issue structure without actually mutating the tracker") with concrete trigger conditions.

5 / 5

Trigger Term Quality

"Linear-ready", "tracker-ready", "issue structure", and "trace work" give good keyword coverage with a synonym pair (Linear/tracker), though phrases like "ticket" or "break down work" that users would naturally say are missing.

4 / 5

Distinctiveness Conflict Risk

The planning-only scope and "without actually mutating the tracker" boundary carve a clear niche with minimal conflict risk, though overlap remains with sibling stage skills (e.g. slice-spec) in the same lifecycle family.

4 / 5

Total

17

/

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-tracker-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.