CtrlK
BlogDocsLog inGet started
Tessl Logo

plan-mode

Structured planning mode for autonomous task execution. Creates plans as MemoryDocs, executes via Missions, tracks progress with live checklist.

56

Quality

64%

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-mode/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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, actionable, and concise with clear sequencing and an explicit failure-recovery loop; its main weakness is the lack of a pre-execution validation checkpoint before autonomously firing a mission.

Suggestions

Insert an explicit validation gate before mission_fire (e.g., re-confirm the plan's steps and success criteria are concrete and safe) to add a checkpoint to the destructive/autonomous execution path.

Specify the parameter shapes for mission_create and mission_fire (and the plan_update payload) so the guidance is fully copy-paste ready.

Tighten the repeated 'When asked to... (message contains [PLAN MODE] X)' headers into a single shared trigger-conventions note to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is largely lean: numbered steps, a compact plan-document template, and no padding about what plans or missions are; the only mild redundancy is the repeated 'When asked to... (message contains [PLAN MODE] X)' framing across sections.

4 / 5

Actionability

It specifies concrete tool calls (memory_search, memory_write, plan_update, mission_create, mission_fire, mission_list) and exact user-facing message strings, with minor gaps such as the parameter shapes for mission_create/mission_fire not being fully shown.

4 / 5

Workflow Clarity

Each operation (create, approve, execute, status, list, revise) is a clearly sequenced numbered list with an explicit failure feedback loop; the gap is that approving fires an autonomous, batch-like mission without a pre-execution validation gate confirming the plan is sound.

4 / 5

Progressive Disclosure

No bundle files are needed and none are referenced; the ~107-line body is well-organized into clearly labeled sections by intent, which per the rubric's simple-skill guidance warrants a 5 for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

51%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 states concrete capabilities in third person and occupies a fairly distinct niche, but it omits any explicit 'Use when...' trigger guidance and leans on internal jargon rather than natural user phrases.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases such as 'make a plan', 'plan out', or 'step-by-step plan' to lift completeness and trigger-term quality.

Replace or gloss internal jargon ('MemoryDocs', 'Missions') with user-facing terms so the description reads as something a user would naturally say.

Briefly surface the other plan operations (approve, revise, status, list) to broaden capability coverage toward a comprehensive description.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Creates plans as MemoryDocs, executes via Missions, tracks progress with live checklist') but does not comprehensively enumerate sub-tasks (approve, revise, list, status) covered in the body, so it stops short of 5.

4 / 5

Completeness

It clearly states what the skill does but provides no explicit 'Use when...' trigger guidance; per the rubric a missing when-clause caps completeness at 3.

3 / 5

Trigger Term Quality

The description relies on technical jargon ('MemoryDocs', 'Missions', 'live checklist') and omits natural user phrases like 'make a plan' or 'plan out'; the only trigger terms live in the activation block, not the description itself.

2 / 5

Distinctiveness Conflict Risk

'Structured planning mode for autonomous task execution' carves a recognizable niche distinct from generic skills, though 'planning/task execution' is broad enough to risk minor overlap with other task-management skills.

4 / 5

Total

13

/

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.

Validation15 / 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
nearai/ironclaw
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.