CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spek-plan-epic

Plan every outstanding spec of an epic in one request, running the standard plan workflow for each spec through separate agents in dependency order. Use for "plan this epic", "plan the epic", "plan <epic name>", or "plan all the specs in this epic".

Quality

93%

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

88%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 highly actionable, well-sequenced orchestration skill: every step is backed by exact commands, explicit state checks, and recovery paths. The only trimmable fat is a few rationale passages and one dated empirical note, and the child-prompt material could live in a reference file.

Suggestions

Move the dated headless-session observation (2026-10-24, Claude Code 2.1.310) out of the operational paragraph into a brief 'Why' note or reference, keeping only the rule itself inline.

Extract the Step 3 child-prompt checklist into a reference template file so children can be handed it verbatim and the body stays an overview.

Tighten the headless-session paragraph to the rule plus a one-line reason; the current multi-clause justification costs tokens without changing behavior.

DimensionReasoningScore

Conciseness

The body is dense, operational, and free of explanations Claude already knows, but a few passages could be tightened — notably the headless-session rationale paragraph and the inline dated probe record ('recorded on 2026-10-24 with Claude Code 2.1.310'), which is time-sensitive detail not placed in a dedicated section.

4 / 5

Actionability

Fully executable throughout: exact CLI commands with JSON payloads ('spektacular plan new --data "{\"name\":\"<spec>\",\"orchestrated\":true}"'), exact first-line hand-back formats (DONE:/QUESTION:/FAILED:), and concrete per-state actions for every loop iteration.

5 / 5

Workflow Clarity

An explicit 8-step sequence with a status-JSON-driven loop, validation checkpoints (re-read status before every action, loop until status reports nothing left), and full error-recovery paths (resume prompts, cut-off restart handling, stopping mode).

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear step headers and sub-sections; no bundle files exist, and most content is appropriately inline for an orchestrator that needs it all at once. Minor gap: the Step 3 child-prompt checklist and hand-back contract are candidates for a reference template.

4 / 5

Total

18

/

20

Passed

Description

95%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 strong description: it states a clear, concrete capability and gives explicit, natural trigger phrases in third person. Its only weakness is that it under-represents the settle-decisions and summary-writing half of the workflow.

DimensionReasoningScore

Specificity

Names several concrete actions — 'running the standard plan workflow for each spec through separate agents in dependency order' — but omits workflow stages the body performs (settling cross-plan disagreements, writing the planning summary, the end-of-planning review), leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both what ('Plan every outstanding spec of an epic in one request...') and when ('Use for...') with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

'plan this epic', 'plan the epic', 'plan <epic name>', 'plan all the specs in this epic' cover the natural phrasings a user would say, including common variants, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche — epic-level planning through per-spec child agents — with trigger phrases distinct from single-spec planning skills, so conflict risk is minimal.

5 / 5

Total

19

/

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

nicholasjackson/tcgreplay

Path

skills/spek-plan-epic/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.