CtrlK
BlogDocsLog inGet started
Tessl Logo

track-management

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

81

2.40x
Quality

75%

Does it follow best practices?

Impact

96%

2.40x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/track-management/SKILL.md

The canonical home for this skill is track-management in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable and the track lifecycle is sequenced with genuine validation checkpoints and checklists, which are its strongest qualities. Its weaknesses are structural: significant duplication between the Track Lifecycle and Track Operations sections, and a monolithic layout that inlines ~300 lines of template/reference material that should be split into one-level-deep reference files.

Suggestions

Split the spec.md template, plan.md template, tracks.md registry format, and metadata.json field reference into references/ files, keeping SKILL.md as a concise overview with clearly signaled links.

Merge the redundant "Track Operations" section into "Track Lifecycle" - both cover creating, starting, completing, and reverting tracks with overlapping steps.

Trim the "Best Practices" list, which restates the Track Sizing Guidelines and Quality Checklists sections verbatim in condensed form.

DimensionReasoningScore

Conciseness

Most content is project-specific and necessary (templates, marker tables, ID formats), but "Track Operations" (lines 373-411) substantially duplicates the "Track Lifecycle" section (lines 89-155), and "Best Practices" re-states the sizing and checklist sections. This is more than the minor trimming of anchor 4, but the bulk is not filler, so it sits above anchor 2.

3 / 5

Actionability

Fully concrete throughout: copy-paste-ready spec.md and plan.md templates, a complete metadata.json example, an exact status-marker table with real examples (`abc1234`), concrete track ID examples, and specific commands (`/conductor:new-track`, `/conductor:revert`). For an instruction-only skill this is copy-paste-ready guidance covering the common cases.

5 / 5

Workflow Clarity

The creation-implementation-completion lifecycle is explicitly sequenced with verification tasks after each phase, checkpoint approval gates ("Wait for checkpoint approval", "Record checkpoint SHA"), blocked-track error handling, and two dedicated quality checklists. Matches the anchor for explicit validation steps, error paths, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so everything is inlined in a single ~594-line SKILL.md. Internal section headers are well-organized (better than anchor 2's minimal structure), but roughly 300 lines of reference material - the spec.md/plan.md templates, registry format, metadata.json schema, and track patterns - clearly belongs in separate reference files, matching anchor 3.

3 / 5

Total

16

/

20

Passed

Description

73%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 well-formed description with an explicit 'Use this skill when' trigger, a distinct niche, and useful artifact keywords (spec.md, plan.md). Its main weakness is action specificity - the verbs (creating, managing, working with) are generic rather than naming the concrete operations the skill performs.

Suggestions

Replace the generic verbs with concrete operations, e.g. "Creates and manages Conductor tracks: writes spec.md requirements, builds phased plan.md task breakdowns, and maintains the tracks.md registry through completion or revert."

Add natural trigger synonyms users might say, such as "work items", "task tracking", or "tracks.md" to widen when-matching.

State the distinct track types (feature, bug, chore, refactor) as trigger terms since users may ask by work category rather than saying 'track'.

DimensionReasoningScore

Specificity

"creating, managing, or working with" are generic verbs with no concrete distinct actions, but "Applies to spec.md, plan.md, and track lifecycle operations" names concrete artifacts. Matches anchor 3 (domain plus 1-2 concrete actions) rather than 4, which expects several specific actions.

3 / 5

Completeness

Both what ("creating, managing, or working with Conductor tracks - the logical work units...") and when ("Use this skill when...") are explicitly present. Falls short of anchor 5 because the 'what' is circular - the actions are generic verbs on the domain rather than concrete capabilities like writing specs or registering tracks.

4 / 5

Trigger Term Quality

Good natural keyword coverage: "Conductor tracks", "spec.md", "plan.md", "features, bugs, and refactors", "track lifecycle" are phrases a user would plausibly say. Missing common variations such as "work items", "tasks", or "tracks.md" registry, so not anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Conductor tracks" with its spec.md/plan.md artifacts is a clearly distinct niche with dedicated trigger terms; minimal conflict risk with generic document or task-management skills.

5 / 5

Total

16

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (594 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 4 missing

Warning

Total

13

/

16

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.