CtrlK
BlogDocsLog inGet started
Tessl Logo

implement-mainspec

Implements a mainspec end-to-end by auto-detecting mode. Sequential mode (≤3 slices) commits slices in order on the current `feature/<feature>` branch. Parallel mode (>3 slices) uses dependency-aware tiered execution with per-slice worktrees, branches, PRs, and auto-merge into the feature branch. Agent-first — invoked headless by the harness dispatcher with the feature slug as its single argument. No human-in-the-loop, no approval gates.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/sdd/implement-mainspec/SKILL.md

The canonical home for this skill is implement-mainspec in tdg-ninja/context-specs-factory-ai

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 a well-structured, highly actionable orchestration spec with strong workflow clarity and explicit validation/feedback loops for its destructive git operations. Its weaknesses are repetition that hurts conciseness and a heavy main body that blurs the overview-vs-reference split.

Suggestions

De-duplicate the delegation/git-commit instructions: define the per-slice spawn + commit + push sequence once and reference it from both the Sequential and Tier 0 sections instead of restating it.

Move the consolidated DO/DON'T Guidelines list to a reference file or trim it to only rules not already stated in the phase sections, since most guidelines restate in-phase instructions.

Relocate the TODO Structure and Signal Processing sections into a reference file (or fold signal handling into the subagent-prompt-template) so SKILL.md reads as a lean overview pointing to detail.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and uses efficient command blocks, but it is padded by repetition — the sequential/parallel delegation and git-commit steps, the 'no approval gates' rule, and the DO/DON'T guidelines restate material already covered in the phase sections, so it could be tightened.

3 / 5

Actionability

It provides concrete, copy-paste-ready shell commands (git worktree add, gh pr create --head/--base, gh pr merge --merge) and explicit subagent spawn parameters with naming conventions; the only minor gap is the referenced scripts/bootstrap-worktree.sh not being present in the bundle, though it is handled gracefully with a warning.

4 / 5

Workflow Clarity

A clear Phase 0–5 sequence with explicit validation checkpoints (precondition verify-and-exit, idempotency resume detection, bounded signal-fix loop with max_signal_iterations: 3) and feedback loops (signal validate→fix→retry, merge-conflict auto-resolve or exit for dispatcher retry) covers the destructive/batch git operations appropriately.

5 / 5

Progressive Disclosure

References are one level deep, real, and clearly signaled with when-to-read guidance (subagent-prompt-template.md, error-handling.md, release-strategy.md) and the compute_tiers.py script is invoked directly; however the 539-line main body inlines substantial content (TODO structures, signal processing, full guidelines) that keeps it from being a lean overview pointing to detail.

4 / 5

Total

16

/

20

Passed

Description

67%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 is specific, concrete, and highly distinct, clearly conveying a complex two-mode implementation workflow. Its main weakness is the missing explicit 'Use when...' trigger guidance, which limits completeness and natural trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when implementing a mainspec end-to-end, when the dispatcher fires /implement-mainspec, or when the user asks to implement all slices of a feature spec.'

Include a few natural synonyms alongside 'mainspec' (e.g. 'feature spec', 'slice implementation', 'spec runner') so the description matches phrasings a user would actually say.

Lead with the user-facing trigger before the internal dispatcher detail, so the 'when' reads as guidance rather than an invocation mechanism.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — auto-detects mode, commits slices in order, dependency-aware tiered execution, per-slice worktrees, branches, PRs, and auto-merge — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

The 'what' is clearly stated (end-to-end mainspec implementation with two modes), but the 'when' is only weakly implied via the dispatcher invocation mechanism and there is no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

It surfaces the key domain term 'mainspec' and the invocation form, but offers few natural synonyms or variations a user would say; coverage is relevant but incomplete for a narrow specialized domain.

3 / 5

Distinctiveness Conflict Risk

The 'mainspec' / tiered-execution / feature-branch niche is highly specific with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (540 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
tdg-ninja/context-specs-claude-code
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.