execute-plan

Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

71%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 compact, well-structured instruction skill with a clear step sequence and a real verification checkpoint. Its weaknesses are token padding (the hardcoded '20 tasks' recital and a redundant Example Usage section) and an unspecified failure path: the `[!]` FAILED status is defined but never handled.

Suggestions

Remove the hardcoded recital 'All the 20 tasks will be addressed' or parameterize it by the actual task count; plans vary in size and the fixed number is inaccurate padding.

Delete or drastically shorten the 'Example Usage' section, which restates Execution Steps 2-6 and duplicates the Task Status Format table.

Add a short error-recovery step for `[!]` FAILED tasks (e.g., when a task fails, mark it `[!]`, attempt a fix, and re-mark `[~]`/`[x]`) so the defined failure status has a concrete handling path.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the 'Commitment to Completion' section (including a hardcoded recital of 'All the 20 tasks' regardless of actual plan size) and the 'Example Usage' section that largely restates steps 2-5 are unnecessary padding. Not 4 because there are several removable elements, not just minor trims; not 2 because the core steps and status table are tight.	3 / 5
Actionability	Concrete, executable guidance: a specific status-marker table (`[ ]`/`[~]`/`[x]`/`[!]`) and six numbered steps. Minor gaps: no instruction for handling `[!]` FAILED tasks, and 'identify pending tasks based on `task_status`' is ambiguous relative to the bracket markers. Not 5 because of these missing details; not 3 because the guidance is genuinely executable, not pseudocode.	4 / 5
Workflow Clarity	Clear sequence with an explicit verification checkpoint (STEP 6: re-read the plan file to verify completion), so the batch-operation validation cap does not apply. Not 5 because there is no error-recovery loop for FAILED tasks despite defining the `[!]` status; not 3 because verification is explicitly present, not merely implied.	4 / 5
Progressive Disclosure	The body is under 50 lines with no need for external references, and content is organized into clearly headed sections (Commitment, Execution Steps, Task Status Format, Example Usage), matching the simple-skill exception for a full score.	5 / 5
	Total	16 / 20 Passed

Description

82%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 what the skill does, gives an explicit and concrete 'Use when' trigger including a recognizable file-path pattern, and occupies a distinct niche. The only weakness is that the capability list is thin (one or two actions) compared to the most comprehensive examples.

Dimension	Reasoning	Score
Specificity	"Execute structured task plans with status tracking" names the domain and 1-2 concrete actions (executing plans, status tracking) but does not enumerate several specific actions. Not 4 because it lacks the multi-action coverage of 'Extracts text, fills forms, converts pages'; not 2 because the actions go beyond minimal domain naming.	3 / 5
Completeness	Explicitly answers both what ("Execute structured task plans with status tracking") and when ("Use when the user provides a plan file path in the format ... or explicitly asks you to execute a plan file") with concrete trigger phrases, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ("execute a plan file", "plan file path") plus the concrete `plans/{current-date}-{task-name}-{version}.md` pattern, giving good keyword coverage. Not 5 because common variations like "run the plan", "work through the tasks", or "task list" are missing; not 3 because coverage is genuinely good rather than partial.	4 / 5
Distinctiveness Conflict Risk	Clear niche: executing structured plan files identified by a specific path format. Triggers are distinctive and unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tailcallhq/forgecode
Path: crates/forge_repo/src/skills/execute-plan/SKILL.md
Commit: 8eb3e24

Reviewed: 3 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.