Skip to content
cccskills
FreePublished on GitHub

taste

Use when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Not for tasks that require source or remote-system changes.

The English summary is being prepared. Showing the original description.

See how to install

Files included (5)

  • SKILL.md6.4 KB
  • agents/openai.yaml167 B
  • references/anchors.md7.0 KB
  • references/charter.md3.4 KB
  • references/examples.md5.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Taste

Contract

FieldBound contract
TriggerUser asks 'overkill?', 'elegant?', 'audit', or 'taste-test this', or asks to set a taste register
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectAudit returns a verdict table and ranked fixes in chat; anchor mode persists the register best-effort; no files are written.
DoneA per-anchor verdict table with ranked top-3 fixes is returned, or the taste register is loaded in anchor mode.

Inputs

  • The artifact or decision to judge (required for audit mode).
  • No inputs required for anchor mode beyond the invocation.

Procedure

Mode selection

Auto-detect from the user's phrasing, with slash-arg override:

  1. User wording matches overkill?, elegant?, audit, taste-test this, judge this → audit mode.
  2. User wording matches taste anchor, taste mode, taste register, or anticipates producing fresh work → anchor mode.
  3. Anything else → audit (default; cheaper to run; no behavior commitment).
  4. Explicit override: /taste audit or /taste anchor. Override always wins.

Audit mode

  1. Walk the eleven anchors one at a time against the artifact.
  2. For each anchor: state the anchor, judge the artifact (pass / warn / fail), cite the Side A or Side B charter row when violated, and write a concrete fix.
  3. When two anchors fail with conflicting fixes (e.g., Restraint says compress, Generosity says expand), surface the tension explicitly. Do not auto-pick. Tie-break is user-led.
  4. Close with the top-3 ranked fixes.

Anchor mode

  1. Load the charter and anchors as imperatives for subsequent responses.
  2. Persistence is best-effort: applies until the user signals "stop taste" or "normal mode" OR context is compacted, whichever comes first.
  3. Re-invoke /taste anchor if drift is observed.

Auto-clarity exception

Suspend the register temporarily for:

  • Destructive or irreversible operation confirmations (e.g., git push --force, rm -rf).
  • Security or data-loss warnings.
  • Multi-step procedures where order or atomicity matters and the judgment register would obscure structure.
  • Direct user clarification requests.

Resume the register once the high-stakes section ends.

The two-sided charter

Side A: slop (centroid-AI default convergence): generic openers ("Sure!", "Of course"), hedge-stacks ("perhaps it might be"), validation phrases ("you're absolutely right"), AI-flat prose with no rhythm, default palettes, defensive nil-checks where impossible, 50/50 decision hedges that pick nothing.

Side B: overkill (decoration covering thin ideas): gradient stacks on every section, thesaurus-soup prose ("orchestrate the comprehensive synthesis of"), abstraction towers (4 layers where 1 suffices), complexity-flex masking absent conviction, ceremony that performs depth without delivering it.

DomainSide A (slop)Side B (overkill)
Prose"I think this might possibly help...""We orchestrate a paradigm shift across"
Codetry { x } catch { /* swallow */ }Factory<Builder<Strategy<T>>>
DesignDefault purple-blue gradientGradient on every section + glow + glass
Decision"Both options have merit, so..."12-criterion weighted scoring matrix

Anchors

Eleven anchors apply across prose, code, design, and decisions:

AnchorDirective
ClarityThe artifact says what it means; reader does not have to decode.
HierarchyImportant looks important; secondary supports.
IntentEvery choice is committed; nothing reads as "I let the default decide."
CoherenceParts agree; tension only where deliberately staged.
RestraintDefault posture; compress before adding.
GenerosityGives more than required at the right moment.
HonestyNo decoration covering missing depth; no slop covering missing POV. Care finishes the unseen.
One strong momentExactly one commitment carries the lift; the rest supports.
InvariantsThe artifact names what must hold; preconditions, postconditions, and invariants are explicit.
AudienceThe artifact enters through the reader's frame, not the author's.
EmptinessThe artifact leaves space the user completes; the least assertion.

Failure and recovery

Failure classResponse
Artifact too short or ambiguous to judgeReturn "insufficient surface" with the specific missing element; do not fabricate verdicts.
Anchors produce conflicting fixesSurface the tension; do not auto-pick. Tie-break is user-led.
Anchor mode drift after context compactionRe-invoke /taste anchor; do not assume persistence.
User artifact is in a domain with no charter rowApply the anchors directly; note the domain gap in the verdict table.

No partial-result fabrication. If fewer than eleven anchors can be judged, return only the judged anchors and name the blocker.

Output

Audit mode

Anchor             | Verdict | Citation              | Fix
-------------------|---------|-----------------------|----------------------------
Clarity            | pass    |                       |
Hierarchy          | warn    | Side A: AI-flat prose | Lead with the verdict line
Intent             | fail    | Side A: hedge-stack   | Pick one; drop "might"
Coherence          | pass    |                       |
Restraint          | warn    | Side B: ceremony      | Cut the framing paragraph
Generosity         | pass    |                       |
Honesty            | pass    |                       |
One-strong-moment  | fail    | Side A: 50/50 hedge   | Commit to one direction
Invariants         | pass    |                       |
Audience           | pass    |                       |
Emptiness          | pass    |                       |

Top-3 fixes: 1. Pick one direction (Intent + One-strong-moment).
             2. Lead with the verdict (Hierarchy).
             3. Cut the framing paragraph (Restraint).

Anchor mode

The register is loaded; subsequent responses hold the eleven anchors as imperatives. No table is emitted.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

af-xdp

Free

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

See all skills by OutlineDriven

Report a problem with this skill