CtrlK
BlogDocsLog inGet started
Tessl Logo

planning-with-files

Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.

64

Quality

77%

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/planning-with-files/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable with concrete templates and a clear workflow, but it carries some redundancy and its advanced references point to files that are not present in the bundle.

Suggestions

Create the missing reference.md and examples.md (or remove the links) so the Advanced Patterns pointers resolve to real files.

Trim editorializing and the Critical Rules section that restates the Core Workflow to tighten conciseness.

Move the full templates into referenced files, keeping only a compact Quick Start inline, to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly lean templates and tables, but editorializing ("Work like Manus", "This is non-negotiable") and redundancy between Critical Rules and the Core Workflow add tokens that could be trimmed.

2 / 3

Actionability

Provides copy-paste-ready task_plan.md and notes.md templates, concrete filenames, and a 3-file pattern table — specific and executable rather than abstract.

3 / 3

Workflow Clarity

Quick Start gives a numbered 4-step sequence and the Core Workflow plus Loop-in-Detail lay out a clear before/after cadence; this is a planning skill so destructive-operation validation gates are not required.

3 / 3

Progressive Disclosure

Structure is decent and references are one-level and clearly signaled, but the referenced reference.md and examples.md do not exist in any bundle directory, leaving navigation broken, and large templates sit inline rather than in separate files.

2 / 3

Total

10

/

12

Passed

Description

77%

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 is specific and complete with an explicit trigger clause, clearly answering both what and when. It is somewhat generic on the planning/tracking axis, leaving moderate overlap with other planning-oriented skills.

Suggestions

Sharpen trigger terms toward user-uttered phrasing (e.g., "long-running tasks", "track progress across sessions") to lift trigger_term_quality.

Tie the niche more tightly to durable on-disk artifacts to reduce overlap with in-memory planning skills and improve distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "persistent planning, progress tracking, or durable notes on disk" plus "multiple tool calls, research steps, verification loops" — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Explicitly answers what ("persistent planning, progress tracking, or durable notes on disk") and when via an explicit "Trigger when a task will likely span multiple tool calls..." clause, satisfying both halves.

3 / 3

Trigger Term Quality

Relevant keywords like "multi-step work", "planning", "progress tracking", and "research steps" are present, but they are framed for the agent rather than as terms a user would naturally utter, and common variations are thin.

2 / 3

Distinctiveness Conflict Risk

The file-on-disk planning niche is somewhat distinct, but "planning" and "progress tracking" overlap broadly with general planning/TodoWrite-style skills, so conflict risk remains.

2 / 3

Total

10

/

12

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: 2 missing

Warning

Total

14

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
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.