CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plan-mode

Holistic, system-aware planning before implementing non-trivial tasks. Use when the task involves new features, architectural decisions, multi-file changes, unclear requirements, or multiple valid approaches. Triggers on "/plan", "plan this", "design an approach", "let's plan first".

64

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

A strong, well-sequenced planning workflow with explicit validation checkpoints, feedback loops, and concrete artifacts (PLAN.md, a structured plan template, an 8-question design checklist). The main improvements are reducing redundancy between the Planning Doctrine and the step content, and splitting the doctrine or template into a reference file for a leaner overview.

Suggestions

Merge the Planning Doctrine bullets into Step 3 (Design) where the same ideas reappear as questions, cutting roughly 10 lines of redundancy.

Move the plan-structure template and Planning Doctrine into a single reference file (e.g., references/planning-doctrine.md) and keep SKILL.md as a lean step-by-step overview.

Add one short filled-in example of a plan entry (Summary/System Impact/Changes bullet) so the template is unambiguous to execute.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no filler explaining what planning is), but the Planning Doctrine bullets ('Choose the smallest coherent solution', 'Expand scope only when it simplifies the system') substantially repeat ideas restated in Step 3's questions ('What is the smallest solution that keeps the system coherent?') and Step 4's review items. It is not 4 because the doctrine-to-steps redundancy is a noticeable tightening opportunity, and not 2 because there is no padding or explanation of concepts Claude already knows.

3 / 5

Actionability

Concrete, executable guidance throughout for an instruction-only skill: a specific output file ('Write your plan to a PLAN.md file in the project root'), an explicit plan structure template, the 8-question design checklist, and direction to 'Launch parallel explorations... Give each exploration a specific, distinct search focus'. It is not 5 because a small worked example of a plan entry (e.g., a filled-in 'Changes' bullet) would make the template copy-paste ready, and not 3 because the guidance is specific and complete enough to execute without inference.

4 / 5

Workflow Clarity

A clearly sequenced six-step workflow (Explore -> Clarify -> Design -> Review -> Present -> Implement) with explicit validation checkpoints ('Read the critical files your design depends on to verify your assumptions', 'run the verification steps from the plan to confirm all items were completed correctly'), a pre-finalization checklist (the 8 design questions), and feedback loops ('If the user has feedback, revise accordingly'; 'Ask remaining clarifying questions if anything is still ambiguous').

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well organized into clearly headed sections (doctrine, plan file, six steps), so navigation is easy. It is not 5 because at ~110 lines the Planning Doctrine and the plan-structure template are candidates for a one-level-deep reference file, which would keep SKILL.md a leaner overview; it is not 3 because nothing is buried and all structure present is appropriate.

4 / 5

Total

16

/

20

Passed

Description

78%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 that explicitly covers both what the skill does and when to use it, with natural trigger phrases. Its main weakness is that 'what' stays at the abstraction level of 'planning' without naming the concrete activities (explore, clarify, design, present a plan file) that the skill actually performs.

Suggestions

Enumerate 2-3 concrete actions in the description, e.g., 'Explores the codebase, resolves ambiguities with the user, and writes a concrete PLAN.md with system impact and verification steps.'

Add one or two common trigger variations such as 'make a plan' or 'plan this out' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Holistic, system-aware planning before implementing non-trivial tasks") with a single generic action; it does not list the concrete actions the skill performs (explore, clarify, design, write a plan). It is not 4 because 'holistic' and 'system-aware' are descriptive adjectives rather than additional specific actions, and not 2 because the action and domain are stated clearly rather than minimal or generic.

3 / 5

Completeness

It explicitly answers both what ('Holistic, system-aware planning before implementing non-trivial tasks') and when ('Use when the task involves... Triggers on...') with concrete trigger phrases, matching the anchor for a complete description.

5 / 5

Trigger Term Quality

Trigger phrases '"/plan"', '"plan this"', '"design an approach"', '"let's plan first"' are natural terms a user would say, backed by situational triggers ('new features, architectural decisions, multi-file changes, unclear requirements, or multiple valid approaches'). It is not 5 because common variations and synonyms (e.g., 'make a plan', 'how should we approach this', 'architecture review') are missing.

4 / 5

Distinctiveness Conflict Risk

The '/plan' and 'plan this' triggers carve a fairly distinct niche, but the situational scope ('new features, architectural decisions, multi-file changes') is broad and overlaps with general planning or architect-type skills. It is not 5 because of that overlap risk, and not 3 because the explicit trigger phrases make confusion unlikely.

4 / 5

Total

16

/

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

Kiz8-Team/open-agents

Path

.agents/skills/plan-mode/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.