CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plan

Lightweight planning with optional interview

Quality

61%

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/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.

The body is a well-structured, operational policy document with clear mode routing, concrete steps, defined output formats, and real validation checkpoints. Its main weaknesses are redundancy (the deprecation note and quality thresholds each repeated multiple times) and a slightly over-inlined Advanced section.

Suggestions

State the "omx explore is deprecated" guidance once (in Tool_Usage) and remove the duplicate in Execution_Policy.

Consolidate the 80%/90% quality thresholds into a single location (Final_Checklist or the Advanced review criteria) and reference it elsewhere instead of repeating it three times.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows, but contains clear repetition: the "omx explore is deprecated" note appears in both Execution_Policy and Tool_Usage, and the 80%/90% quality thresholds appear three times (Execution_Policy, Final_Checklist, Advanced). This is 'mostly efficient but could be tightened' rather than 4, which allows only minor trimming.

3 / 5

Actionability

Guidance is concrete and executable: a mode-selection table with exact triggers, numbered steps per mode, a defined output template ("Requirements Summary, Acceptance Criteria (testable), Implementation Steps..."), specific tooling ("omx question with OMX_QUESTION_RETURN_PANE"), and the save path .omx/plans/. Minor gaps (no example plan, no file-naming convention) keep it below 5.

4 / 5

Workflow Clarity

Each of the three modes has a clear numbered sequence, and validation checkpoints are present via the Final_Checklist, the Critic verdict (APPROVED/REVISE/REJECT), and explicit stop conditions ("Stop interviewing when requirements are clear"). Minor gaps such as no iteration cap on the interview loop keep it below 5; no destructive/batch cap applies.

4 / 5

Progressive Disclosure

A single well-organized file with clearly labeled sections (Purpose, Use_When, Steps, Tool_Usage, Escalation, Final_Checklist, Advanced) and no broken or buried references. At ~90 lines it exceeds the under-50-line simple-skill exemption, and the small Advanced section (question classification, review criteria) is arguably inline content that could be split out, matching anchor 4's 'minor organization gaps' rather than 5.

4 / 5

Total

15

/

20

Passed

Description

36%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 is a terse six-word phrase that names the domain but omits concrete capabilities, natural trigger phrases, and any "use when" guidance. It under-sells the skill's actual features (work-plan generation, Socratic interviewing, plan review) and creates overlap risk with other planning/execution skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user says 'plan this', 'let's plan', or 'scope this out' before implementation, or asks to review an existing plan."

List the concrete capabilities: creates evidence-backed work plans with testable acceptance criteria, runs a Socratic interview to scope vague requirements (--interview), and evaluates existing plans (--review).

Include natural synonyms such as "planning", "work plan", "requirements gathering", and "scope" to improve trigger matching and distinguish it from direct-execution skills.

DimensionReasoningScore

Specificity

"Lightweight planning" is a generic action naming only the domain, and "optional interview" describes a mode rather than a concrete capability; no concrete actions like creating work plans, defining acceptance criteria, or reviewing plans are stated. This matches the anchor 'Names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions.

2 / 5

Completeness

The 'what' is vague ("Lightweight planning" conveys only the domain) and the 'when' is entirely absent — no "Use when..." clause or equivalent trigger guidance exists. This matches anchor 2 ('Has a vague what and no when') rather than 3, whose example lists multiple concrete actions as a clear 'what'.

2 / 5

Trigger Term Quality

"planning" is a keyword users would naturally say, but common variations and synonyms ("plan this", "scope", "requirements gathering", "roadmap") are missing and "interview" is internal jargon. Fits 'Some relevant keywords but missing common variations or synonyms', not 4 which requires good coverage with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

"Lightweight planning" broadly overlaps with other planning and task-execution skills, with "optional interview" as the only distinguishing feature. It is somewhat specific but could still trigger for the wrong skill, matching anchor 3 rather than 4, which requires mostly distinct triggers.

3 / 5

Total

10

/

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

Yeachan-Heo/oh-my-codex

Path

skills/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.