harden-task-file

Solid

Harden a manifest-dev task guidance file for one-shot quality — either /define's quality-gate/Default set or figure-out's probe set. Iterates: orthogonality gap analysis, user-approved additions, prompt review, fix, converge. Use when a task file needs comprehensive coverage or "harden task file".

AI & Automation 73 stars 10 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
62
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

**User request**: $ARGUMENTS Systematically harden a /define task guidance file until manifests built from it produce deliverables that don't need iteration. If no arguments, ask which task file to harden. ## Context Task files come in two parallel, decoupled sets, each keyed by task type and hardened for one-shot quality. Harden whichever set the target file belongs to: - **`/define`'s task files** (`claude-plugins/manifest-dev/skills/define/tasks/`) carry encoder data: - **Quality Gates** — Verifiable output properties. Can split into baselines (always enforced) and selectable (meaningful rigor choices) - **Defaults** — process practices always worth doing, carried into the manifest without probing; `/define` decides the encoding, and routes one whose violation would be unsafe or irreversible to a binding invariant rather than advice - **figure-out's task files** (`claude-plugins/manifest-dev/skills/figure-out/tasks/`) carry probing fuel: - **Blind-spot probes** — Non-natural angles the model skips by default (failure modes, pre-mortem fuel), phrased as the question that opens a branch - **Forced trade-offs** — Competing tensions the model must drive to a decision New items must match the depth and structural conventions of the owning skill (`define/SKILL.md` or `figure-out/SKILL.md`) and its existing sibling task files. ## Goal The task file should be comprehensive enough that a manifest built with it surfaces all criteria needed for one-shot quality — figu...

Details

Author
doodledood
Repository
doodledood/manifest-dev
Created
7 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

harden-skill

Use when an agent needs to harden a skill's instructions so they reliably change agent behavior; diagnoses each intended behavior's baseline failure, matches it to the right instruction form, hardens discipline rules against rationalization, and specifies a micro-test protocol rather than editing the skill or running the tests itself.

0 Updated today
tacticaldoll
AI & Automation Listed

harden-issues

Attack acceptance criteria at authoring time — a blind-spot pass over issue files that sharpens criteria with evidence, names invariants, and routes open forks to the human. EXPLICIT INVOCATION ONLY. Use this skill only when the user types the command /harden-issues, or when an upstream issue-drafting pass calls it on freshly drafted slices. Never infer it from wording such as "harden these issues", "pre-batch pass" or "attack the criteria".

0 Updated 3 days ago
roufmlp
AI & Automation Listed

goalforge-harden

goalforge-internal — use entry commands; do not auto-trigger Drive a WP from status `spec` to `hardened` by first running a read-only Tier-2 pre-harden review (a WP-scoped delta that consumes the feature-level Tier-1 audit as data, skipped entirely for a simple WP with a fresh, finding-free Tier-1, and falling back to a whole-feature review when a sibling WP drifted), then delegating to `goalforge-interview` (which drives the `interview` plugin engine) to resolve all open questions — a question may stay open only as a recorded `[risk-accepted]` risk — then advancing `hardened → ready` via human approval, or autonomously under the signal-scoped rule (simple + severity ≤ MEDIUM + non-migration). Use when a WP's open questions must be driven to zero before execution. TRIGGER: /goalforge-harden <wp-path>.

0 Updated 3 days ago
Truncuso