From sdd
Glyph encoding — LLM-facing compression for SPEC.md and spec-adjacent writes. Loaded by /sdd:spec, /sdd:build, /sdd:check. Cuts tokens ~75% vs prose using heavy symbols (→ ∀ ∃ ∴ ⊥ ≤ ≥ ≠ ∈ ∉ § & |) and pipe tables. Triggers on any write to SPEC.md or when user says "glyph", "caveman", "compress this", "be brief". Adapted from JuliusBrussee/cavekit's caveman skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sdd:glyphThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Audience: the LLM reading SPEC.md back into context. Optimised for tokens, not human eyes — math symbols and fragments are fine because the model parses them cheaply.
Audience: the LLM reading SPEC.md back into context. Optimised for tokens, not human eyes — math symbols and fragments are fine because the model parses them cheaply.
Applies to SPEC.md writes, spec-referencing prose, backprop entries.
Does NOT apply to code, error strings, commit messages, PR descriptions, or anything a human reviewer reads on GitHub (use the steno skill in the gh plugin for that).
Prefer over words:
→ 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
Never compress:
src/auth/mw.go.Invariant:
V<n>: <subject> <relation> <condition>
V1: ∀ req → auth check before handler
V2: token expiry ≤ current_time → reject
Bug row (pipe table under §B):
id|date|cause|fix
B1|2026-04-20|token `<` not `≤`|V2
Task row (pipe table under §T):
id|status|task|cites
T3|x|add auth mw|V1,I.api
Status: x done, ~ wip, . todo. Escape literal | as \|.
Interface:
<kind>: <name> → <shape>
api: POST /x → 200 {id:string}
cmd: `foo bar <arg>` → stdout JSON
env: FOO_KEY ! set
Bad:
The system should ensure that every incoming request is properly authenticated before being forwarded to its corresponding handler function.
Good:
V1: ∀ req → auth check before handler
Bad:
We discovered that the token expiration check in the middleware was using a strict less-than comparison operator, which meant tokens were being rejected at the exact moment of their expiry.
Good:
B1: token
<not≤→ reject @ expiry boundary.
Bad:
The POST endpoint at /x accepts a JSON body and returns a 200 response with an object containing the created id.
Good:
api: POST /x → 200 {id}
If cutting a word loses a fact, keep it. Glyph is compression, not amputation.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub kborovik/pilot-skills