spec-loop-plan-task

Choose the planning form for new work and plan it before execution. Use this skill to decide whether the work is taskless, chat-only, a task file, a task file with subtasks, or multiple task files / backlog items, and to create the needed plan for non-trivial implementation work or investigation work that needs its own task.

Quality

41%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/spec-loop-plan-task/SKILL.md

Quality

Content

50%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 content is well-structured and mostly token-efficient, with a clear phase model and gating rules. However, the bulk of executable guidance lives in referenced files that are absent from the bundle, and the inline drafting steps are high-level, capping actionability and workflow clarity.

Suggestions

Either include the referenced guidance files (planning-form-selection-guidance.md, common-task-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md, scenario-and-glossary-guidance.md) in the bundle or inline the minimal concrete steps each planning form requires so the skill is self-contained.

Add a short, explicit step sequence for the core drafting action (e.g. classify -> clarify -> pick planning form -> draft plan sections from common-task-guidance -> request approval) with clear checkpoints, rather than only delegating to external files.

De-duplicate the EXECUTION-needs-approval and phase-exclusivity rules that recur across 'Core rules' and 'Phase model' to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and procedural with no padding explaining concepts Claude already knows, though a few rules are restated across sections (e.g. EXECUTION-needs-approval appears in Core rules and again in Phase model), making it 'efficient with minor instances that could be trimmed'.	4 / 5
Actionability	The skill points to other files ('read and follow planning-form-selection-guidance.md', 'use the shared task guidance from common-task-guidance.md') for the concrete steps, and the SKILL.md body itself gives high-level classification criteria rather than the specific executable steps to draft a plan, so it is 'minimal concrete guidance with high-level hints missing the specifics to execute'.	2 / 5
Workflow Clarity	A clear phase sequence (PLAN -> EXECUTION -> DONE) and classification-then-plan flow are present, and there is an approval checkpoint plus a clarification gate, but the actual drafting workflow is delegated to referenced files and several checkpoints (e.g. validation that a task is 'ready') are only implicitly defined, leaving 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	References are one level deep and clearly named, but the referenced bundle files (planning-form-selection-guidance.md, common-task-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md, scenario-and-glossary-guidance.md) are not present in the bundle, so navigation cannot be verified and the structure is only 'some organization with references present but not confirmable'.	3 / 5
	Total	12 / 20 Passed

Description

33%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 communicates the skill's purpose reasonably but leans on internal Spec Loop terminology rather than natural user triggers and lacks an explicit 'Use when...' clause. It is distinguishable within its niche yet has moderate overlap risk with generic planning skills.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggering situations, e.g. 'Use when starting non-trivial implementation or investigation work that needs a planned, approval-gated task.'

Replace or supplement internal jargon ('Spec Loop task', 'chat-only planning form', 'approval-gated') with natural phrases users would say, such as 'plan new work', 'break work into tasks', or 'decide how to track a piece of work'.

Tighten the directive-as-approval detail out of the description and surface a few concrete actions (classify work, pick a planning form, draft the task plan) to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain (planning-form selection and task planning) and several concrete actions (decide among five planning forms, create the needed plan), but the 'actions' are abstract categories rather than multiple distinct concrete operations, so it sits at 'names domain and 1-2 concrete actions' rather than the comprehensive 5.	3 / 5
Completeness	It states a clear 'what' (choose planning form and plan work before execution) but the 'when' is only weakly implied via the list of work forms; there is no explicit 'Use when...' clause naming concrete triggering situations, which per the rubric caps completeness below 4.	2 / 5
Trigger Term Quality	The only natural user-facing term is 'task' and the directive list ('implement', 'investigate', 'go ahead'); most language is internal jargon ('Spec Loop task', 'taskless', 'chat-only planning form', 'approval-gated') that a user would not naturally say, missing common trigger phrases users actually voice.	2 / 5
Distinctiveness Conflict Risk	The skill is scoped to Spec Loop planning, which is fairly specific, but the broad verbs ('plan it before execution', 'new work') risk overlap with other planning or task-management skills, leaving it 'somewhat specific but could still overlap'.	3 / 5
	Total	10 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 missing, 8 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-plan-task/SKILL.md
Commit: 27df5cc

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

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.