CtrlK
BlogDocsLog inGet started
Tessl Logo

planning-with-files

Work like Manus: Use persistent markdown files as your "working memory on disk."

47

Quality

51%

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/AI-Agents-Safe-Coding-Skills-claude/skills/planning-with-files/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-structured and actionable with clear workflows and a real error-recovery loop, but it is held back by repetition, a conceptual metaphor, and—most seriously—five broken file references that defeat progressive disclosure.

Suggestions

Create the referenced bundle files (templates/task_plan.md, templates/findings.md, templates/progress.md, reference.md, examples.md) or remove/inline the dead links so navigation actually works.

De-duplicate the project-directory placement guidance to a single statement and drop the 'RAM vs Disk' metaphor that restates a concept Claude already knows.

Replace the dead 'Use templates/... as reference' lines in Quick Start with the existing scripts/init-session.sh invocation as the concrete starting command.

DimensionReasoningScore

Conciseness

The body is mostly useful but repeats the project-directory-file-placement note three times (intro table, Quick Start note, and anti-patterns) and includes the conceptual 'Context Window = RAM / Filesystem = Disk' metaphor Claude already knows, fitting the 3 anchor of mostly efficient with some tightening needed.

3 / 5

Actionability

It gives concrete file names (task_plan.md, findings.md, progress.md), explicit update triggers, a decision matrix, and points to two real executable scripts, matching the 4 anchor; the gap is that the referenced templates do not actually exist.

4 / 5

Workflow Clarity

Quick Start provides a clear 5-step sequence with checkpoints (re-read before decisions, update after phase) plus the 3-strike error feedback loop and a 5-question reboot checklist, fitting the 4 anchor; the missing template files leave a minor gap in the documented workflow.

4 / 5

Progressive Disclosure

Although the section structure is clean, 5 of 7 referenced paths are dead links (templates/task_plan.md, findings.md, progress.md, reference.md, examples.md do not exist in the bundle), so navigation to the detail content fails, matching the 2 anchor of broken/buried references rather than a higher well-organized score.

2 / 5

Total

13

/

20

Passed

Description

42%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 conveys a clear core concept but lacks any explicit trigger guidance and omits the natural planning/task keywords a user would say. It is a serviceable one-liner capped by the missing 'when' clause.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. before multi-step (3+ step) tasks, research, or projects spanning many tool calls.

Include natural user phrases like 'plan', 'track progress', 'organize a complex task', and 'recover context' so the skill surfaces when users actually need it.

Drop the metaphor 'working memory on disk' in favor of one more specific concrete action (e.g. 'maintain task_plan.md, findings.md, and progress.md across a session').

DimensionReasoningScore

Specificity

The phrase "Use persistent markdown files as your 'working memory on disk'" names the domain (markdown planning files) and one concrete action (use them persistently), matching the 3 anchor; it does not list multiple specific actions that would push it to 4.

3 / 5

Completeness

A clear 'what' is present (use persistent markdown files as working memory) but the 'when' is entirely absent with no 'Use when...' clause, so per the cap completeness cannot exceed 3.

3 / 5

Trigger Term Quality

It surfaces only "markdown files", "persistent", and the metaphor "working memory on disk"; it omits the natural phrases a user would actually say ("plan a task", "track progress", "organize a multi-step task"), fitting the 2 anchor of missing natural user phrases.

2 / 5

Distinctiveness Conflict Risk

The file-as-working-memory framing is somewhat specific but generic enough to overlap with other planning or note-taking skills, matching the 3 anchor rather than the more narrowly distinct 4 anchor.

3 / 5

Total

11

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.