CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-task-management

Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress

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 ./.claude/skills/skill-task-management-v2/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 delivers strong, concrete guidance — real tool-call shapes, executable git commands, and clearly sequenced workflows with edge-case handling — but at roughly twice the necessary length. Heavy duplication of the checkpoint template, marketing-style padding, and a migration section that belongs in a reference file (referencing a script not present in the bundle) hold it back.

Suggestions

Deduplicate the checkpoint TaskCreate template, which appears nearly in full three times — keep one canonical template in the checkpointing section and reference it elsewhere.

Move the 'Migration from TodoWrite' guide and the 'Example: Full Workflow' into a separate reference file, and fix or remove the reference to scripts/migrate-todos.sh, which does not exist in this bundle.

Cut the 'Benefits' checkmark list and 'The Bottom Line' section, which restate content already covered, and trim version-specific v7.23.0 notes into the migration/deprecated section.

DimensionReasoningScore

Conciseness

The ~670-line body duplicates the full checkpoint TaskCreate template three times (in section 2 'Saving Progress', in 'Best Practices → Context Preservation', and again in 'Example: Full Workflow'), and includes padded sections ('Benefits' checkmark list, 'The Bottom Line') that restate other content — 'noticeably verbose; several unnecessary explanations or padded sections'. Not 3 because the duplication and padding are extensive rather than occasional; not 1 because it doesn't explain concepts Claude already knows and most content is skill-specific.

2 / 5

Actionability

Concrete TaskCreate/TaskUpdate calls with full parameter objects, executable git commands (git status, WIP commit), exact user-facing confirmation messages, and good/poor task examples — 'mostly executable guidance; concrete code or commands with minor gaps'. Not 5 because the JS-flavored snippets (const tasks = TaskList(), console.log, .filter) are illustrative pseudocode rather than how the tools are actually invoked, and placeholders like taskId: "[task-id]" require fill-in.

4 / 5

Workflow Clarity

Each capability is sequenced in numbered steps with state assessment up front (git status, TaskList) and explicit handling of edge cases ('All pending tasks are blocked. Resolve their dependencies...', 'No pending tasks to resume'), plus a Red Flags table — 'clear sequence with most checkpoints present; minor validation gaps'. Not 5 because there are no error-recovery loops (e.g., WIP commit failure, missing checkpoint task) and the 'see more details' branch is underspecified; the destructive/batch cap does not apply since these operations are non-destructive.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), yet the body references "${CLAUDE_PLUGIN_ROOT:-...}/scripts/migrate-todos.sh" which is not part of this bundle, and the 670-line file inlines content that belongs in separate reference files (the v7.22→v7.23 migration guide, the long worked example) — 'some structure but could be better organized... content that should be separate is inline'. Not 2 because the file is well-sectioned with clear headers and a consistent hierarchy rather than a monolithic wall; not 4 because of the inlined bulk content and the dangling script reference.

3 / 5

Total

13

/

20

Passed

Description

50%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 domain and purpose at a middling level: it says what the skill does in broad strokes but not when to use it, and it relies on generic verbs rather than the concrete trigger phrases the skill is designed around. It is serviceable but leaves invocation decisions and skill differentiation to inference.

Suggestions

Add an explicit 'Use when...' clause with the skill's actual trigger phrases, e.g. "Use when the user says 'add to todos', 'save progress', 'checkpoint this', or 'resume tasks'".

Replace generic verbs ('delegate work', 'monitor progress') with the skill's concrete operations: creating checkpoint tasks with completed/in-progress/next breakdowns, WIP commits, and session resume.

Include the natural synonyms users say (todo list, save progress, checkpoint, pick up where we left off) in the description itself rather than only in the separate trigger field.

DimensionReasoningScore

Specificity

The description names the domain ("Manage tasks with Claude Code native tools") and lists actions ("track TODOs, delegate work, and monitor progress"), but these actions are high-level and generic — it omits the skill's core concrete capabilities (checkpointing, resuming, WIP commits), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. Not 4 because the actions listed are abstract rather than specific and coverage of what the skill actually does is incomplete.

3 / 5

Completeness

The 'what' is stated clearly ("Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress"), but there is no 'Use when...' clause or equivalent activation guidance — "use to" expresses purpose, not when to invoke it. Per the guideline, a missing 'Use when' clause caps completeness at 3; not 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"TODOs" and "tasks" are natural terms users would say, but the description misses the common phrases the skill itself lists as triggers — "save progress", "checkpoint this", "resume tasks", "pick up where we left off" — fitting 'some relevant keywords but missing common variations or synonyms'. Not 4 because several natural trigger phrases users actually say are absent.

3 / 5

Distinctiveness Conflict Risk

"Manage tasks with Claude Code native tools" scopes the skill to a niche, but "delegate work" and "monitor progress" are broad phrases that overlap with orchestration, planning, and project-management skills — 'somewhat specific but could still overlap with similar skills'. Not 4 because the generic delegation/monitoring language creates real overlap risk with closely related skills.

3 / 5

Total

12

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (695 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

nyldn/claude-octopus

Path

.claude/skills/skill-task-management-v2/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.