CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context-state-tracker

State persistence across autonomous coding sessions. Use when saving progress, loading context, managing feature lists, tracking git history, or restoring session state.

Quality

76%

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 ./skills/context-state-tracker/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.

The body is a well-structured, largely actionable overview with real code examples, a sequenced workflow containing a verification checkpoint, and genuine one-level-deep references. Its main weakness is token efficiency: the ASCII workflow diagram and inlined format examples duplicate content that belongs in the existing reference files.

Suggestions

Replace the 20-line ASCII workflow box with a compact numbered list (or move it to a reference) to cut decorative tokens without losing the sequence.

Trim the full feature_list.json and claude-progress.txt examples to their essential shape and defer complete schemas to the existing references/STATE-ARTIFACTS.md and references/PROGRESS-FORMAT.md.

Add a validation checkpoint after artifact writes (e.g., re-parse feature_list.json before committing) and brief commit-message guidance to close the workflow's remaining gaps.

DimensionReasoningScore

Conciseness

Quick start, Key Rules, and the references/scripts listings are efficient, but roughly 30 of ~130 lines could be trimmed: the 20-line ASCII workflow box restates what a six-line list conveys, and the full feature_list.json and claude-progress.txt format examples duplicate content already in references/STATE-ARTIFACTS.md and references/PROGRESS-FORMAT.md. This fits 'mostly efficient but could be tightened' rather than the minor-trimming 4.

3 / 5

Actionability

Quick-start code is near copy-paste ready with real signatures (tracker.save_progress(accomplishments=..., blockers=..., next_steps=...) and features.update_status("auth-001", passes=True)), and every referenced script exists in scripts/. Minor gaps remain: project_dir is an undefined placeholder and no CLI or import-path invocation is shown, so it sits at 'mostly executable' rather than fully copy-paste ready.

4 / 5

Workflow Clarity

The workflow clearly sequences SESSION START / WORK / END and includes a verification checkpoint ("Verify feature passes" precedes "Update feature_list.json (passes: true)"), so the destructive-operation validation cap does not apply. Remaining gaps are minor: no validation of written JSON artifacts and no guidance on commit messages despite 'Commit with descriptive message'.

4 / 5

Progressive Disclosure

Structure is good: a concise overview with a clearly signaled, one-level-deep References section (both files exist on disk) and a Scripts section listing all four modules with descriptions. The main gap is that bulky artifact-format examples are inlined where the existing references already cover them, keeping it just below the well-split 5.

4 / 5

Total

15

/

20

Passed

Description

75%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 solid description with an explicit trigger clause, third-person voice, and natural trigger terms covering all five core capabilities. It stops short of top marks because the 'what' stays abstract and concrete artifact names and synonyms are omitted.

Suggestions

Make the 'what' clause enumerate concrete capabilities (e.g., "Persists session state via an immutable feature list, an append-only progress log, and git history") to raise specificity and completeness.

Add natural synonyms and artifact names users might say, such as "resume work", "checkpoint", or "feature_list.json" / "claude-progress.txt", to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists five specific actions ("saving progress, loading context, managing feature lists, tracking git history, or restoring session state"), but they remain at a management-level abstraction without naming concrete artifacts like feature_list.json or claude-progress.txt, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.

4 / 5

Completeness

Both parts are present: a what ("State persistence across autonomous coding sessions") and an explicit "Use when..." clause with concrete triggers. The what is a single abstract noun phrase rather than an enumeration of concrete capabilities, placing it just below the 5 anchor's fully explicit what+when.

4 / 5

Trigger Term Quality

Phrases such as "saving progress", "feature lists", "git history", and "restoring session state" are natural things a user would say, giving good keyword coverage. Common synonyms (e.g., "resume work", "checkpoint") and file extensions are absent, so it fits the 4 anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The niche (cross-session state persistence for autonomous coding) is clearly framed and unlikely to trigger for unrelated skills, but broad phrases like "tracking git history" and "loading context" create minor overlap risk with generic git or context-management skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/context-state-tracker/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.