feat: refresh shared skills catalog

This commit is contained in:
vasily committed 2026-10-30 12:40:16 +08:00
1 parent 98bb35e6fb
commit 418792d1ec
49 files changed
+2273 -2390

No files matched your search

+20 -87
View File
@@ -1,100 +1,33 @@
---
name: caveman
description: >
Token-compression encoding dialect for SPEC.md and spec-adjacent writes (~75% reduction vs prose).
Preserves code identifiers and invariants verbatim while dropping filler and using formal symbols.
Use when writing or editing SPEC.md, when asked to "caveman", "compress this", or "be brief".
concerns: [system-one-balance]
Use compact Caveman notation when explicitly requested, or when editing a spec that already adopts that notation. Ordinary requests to be brief use plain English.
scope: global
---
# Caveman — Spec Encoding
# Compact spec notation
Applies to `SPEC.md` writes, spec-referencing text, and backprop entries.
Does NOT apply to code, error strings, commit messages, or PR descriptions.
Keep technical statements concise without losing conditions, scope, uncertainty,
or modality. Preserve code, identifiers, paths, URLs, versions, numbers, quoted
strings, and data formats verbatim. Plain English is preferable when symbols make
a statement ambiguous; notation does not determine SPEC.md ownership.
---
- `→` leads to/becomes; `∀` every; `∃` exists.
- `!` required; `⊥` forbidden; `?` unknown.
- `≤`, `≥`, `≠`, `∈`, `∉` retain mathematical meanings.
- Write optional behavior and missing values (`null`, `nil`) explicitly; do not
overload unknown/forbidden symbols with those meanings.
- Remove filler and unnecessary articles. Retain negation, quantifiers, honest
hedges, exception conditions, and words needed to distinguish implement from fix.
## Phase 0: Setup and Protocols
Examples:
1. **Grammar Invariants**:
- Drop articles (a, an, the).
- Drop filler (just, really, basically, simply, actually).
- Drop auxiliary verbs where fragments work (is, are, was, were, being).
- Drop pleasantries and hedging ("might", "perhaps", "could be worth").
- Short synonyms: fix > implement, big > extensive, run > execute.
2. **Symbol Table**:
- `→` leads to / becomes / on `<x>`
- `∴` therefore / fix
- `∀` for all / every
- `∃` exists / some
- `!` must / required
- `?` may / optional / unknown
- `⊥` never / forbidden / nil
- `≠` not equal
- `∈` in, `∉` not in
- `≤` at most, `≥` at least
- `&` and, `|` or
- `§` section reference
3. **Preserve Verbatim**:
- Never compress code blocks, paths (`src/auth/mw.go`), URLs, identifiers (`function_name`), numbers/versions, error strings, SQL/JSON/YAML, or quoted strings.
---
## Phase 1: Ingest and Check
1. Confirm target document: `SPEC.md` section, backprop row, or prompt.
2. Verify target is spec or technical invariant, NOT human prose, code, or commit messages.
3. If user asks for prose explanation, switch to standard English.
---
## Phase 2: Processing (Core Logic)
Encode into canonical Caveman shapes:
### 1. Invariant (§V)
```text
V<n>: <subject> <relation> <condition>
V1: ∀ req → auth check before handler
V2: token expiry ≤ current_time → reject
api: POST /x → 201 {id:string}
T3|~|add auth middleware|V1,I.api
```
### 2. Bug Row (§B pipe table)
```text
id|date|cause|fix
B1|2026-04-20|token `<` not `≤`|V2
```
### 3. Task Row (§T pipe table)
```text
id|status|task|cites
T3|x|add auth mw|V1,I.api
```
*Status: `x` done, `~` wip, `.` todo. Escape literal `|` as `\|`.*
### 4. Interface (§I)
```text
<kind>: <name> → <shape>
api: POST /x → 200 {id:string}
cmd: `foo bar <arg>` → stdout JSON
env: FOO_KEY ! set
```
---
## Phase 3: The System One Balance Pass
- **Compression, Not Amputation**:
- If cutting a word loses an invariant or factual boundary, keep the word.
- Never sacrifice precision for token brevity.
- Fail open to standard English when ambiguous.
---
## Phase 4: Output Execution & Verification
1. Output compressed text in valid Markdown.
2. Verify:
- All code tokens, identifiers, and paths are intact.
- All symbols use standard UTF-8 characters (`→`, `∀`, `⊥`, `!`).
- Pipe tables parse cleanly with balanced delimiters.
Use the project's table format and escape literal pipes as needed. Verify that a
reader can recover the exact behavioral claim; no token-reduction target, special
scan, or automatic compression of human-facing reports is required.