@sassywares/skills 0.7.3 → 0.7.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CONCEPTS.md CHANGED
@@ -6,7 +6,7 @@ The repo's `skills/` directory is the only copy of the skills. Consumers install
6
6
 
7
7
  ## Skill
8
8
 
9
- A directory containing `SKILL.md`, discovered by a harness from a project skills directory, a user skills directory, or an installed package. Skills are explicit workflows, not always-on instructions. Most have `disable-model-invocation: true` and are invoked with `/skill:<name>`.
9
+ A directory containing `SKILL.md`, discovered by a harness from a project skills directory, a user skills directory, or an installed package. Skills are explicit workflows, not always-on instructions. The model may invoke any of them, and the user can invoke one directly through their harness (the `sassy-setup` skill's `references/harness.md` lists each harness's command).
10
10
 
11
11
  ## Agent
12
12
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sassywares/skills",
3
- "version": "0.7.3",
3
+ "version": "0.7.5",
4
4
  "description": "Lean, explicit-invocation Agent Skills for shipping fast: plan, work, review, validate, ship.",
5
5
  "type": "module",
6
6
  "license": "MIT",
@@ -5,7 +5,6 @@ description: >-
5
5
  a PR over time — not for a one-shot comment fix or a single CI failure. GitHub
6
6
  (incl. Enterprise) only.
7
7
  argument-hint: "[PR number|URL|blank=current branch] [checkpoint] [merge:on|off] [delete-branch:on|off]"
8
- disable-model-invocation: true
9
8
  ---
10
9
 
11
10
  # Sassy Babysit
@@ -5,7 +5,6 @@ description: >-
5
5
  to commit or save staged/unstaged changes with a repo-appropriate message.
6
6
  Local commit only — no push, no PR.
7
7
  argument-hint: "[branch:current|new <name>]"
8
- disable-model-invocation: true
9
8
  ---
10
9
 
11
10
  # Sassy Commit
@@ -5,7 +5,6 @@ description: >-
5
5
  open or update a PR, or for a PR-description-only flow (writing, rewriting, or
6
6
  describing a PR body).
7
7
  argument-hint: "[PR ref] [branch:new|current] [base:<branch>] [babysit:on|off] [checkpoint] [merge:on|off] [delete-branch:on|off]"
8
- disable-model-invocation: true
9
8
  ---
10
9
 
11
10
  # Sassy Commit, Push, PR
@@ -6,7 +6,6 @@ description: >-
6
6
  maintains the project's concepts file and a pointer in AGENTS.md when useful.
7
7
  Lean on purpose.
8
8
  argument-hint: "[optional context] [mode:manual|auto]"
9
- disable-model-invocation: true
10
9
  ---
11
10
 
12
11
  # Sassy Compound
@@ -9,7 +9,6 @@ description: >-
9
9
  Never commits. Built for context and token
10
10
  efficiency — the orchestrator only writes briefs and reads compact results.
11
11
  argument-hint: "<work brief | findings> [intent reference]"
12
- disable-model-invocation: true
13
12
  ---
14
13
 
15
14
  # Sassy Cycle
@@ -6,7 +6,6 @@ description: >-
6
6
  it through sassy-ship. Never auto-commits. Use when asked to
7
7
  debug or fix a failure.
8
8
  argument-hint: "[issue reference, error message, test path, or description] [branch:infer|current|new]"
9
- disable-model-invocation: true
10
9
  ---
11
10
 
12
11
  # Sassy Debug
@@ -6,7 +6,6 @@ description: >-
6
6
  information only, with mermaid diagrams. Use when asked for a handbook,
7
7
  handover notes, a team reference, or to turn a plan into a readable guide.
8
8
  argument-hint: "[plan path, topic, or brief context]"
9
- disable-model-invocation: true
10
9
  ---
11
10
 
12
11
  # Sassy Handbook
@@ -8,7 +8,6 @@ description: >-
8
8
  next. Use at a phase boundary, when context is getting long, when the user
9
9
  asks to hand off, or to pick up a handoff file.
10
10
  argument-hint: "[mode:write|read] [goal for the next session | handoff file path]"
11
- disable-model-invocation: true
12
11
  ---
13
12
 
14
13
  # Sassy Handoff
@@ -5,7 +5,6 @@ description: >-
5
5
  then close out via sassy-ship after code approval. The orchestrator only
6
6
  coordinates. Best for small plans that one context can hold.
7
7
  argument-hint: "<plan path | brief> [branch:infer|current|new]"
8
- disable-model-invocation: true
9
8
  ---
10
9
 
11
10
  # Sassy LFG
@@ -8,7 +8,6 @@ description: >-
8
8
  Sketches UI on request. No modes, no QA flags. Use when asked to brainstorm,
9
9
  scope, plan, or create a phased plan.
10
10
  argument-hint: "[feature description, requirements, or idea to scope]"
11
- disable-model-invocation: true
12
11
  ---
13
12
 
14
13
  # Sassy Plan
@@ -7,7 +7,6 @@ description: >-
7
7
  (default) asks which to fix, mode:auto fixes all actionable, mode:return only
8
8
  reports. Use when asked to review code. Leaves changes uncommitted.
9
9
  argument-hint: "[PR ref, branch, files, or blank for current changes] [mode:manual|auto|return]"
10
- disable-model-invocation: true
11
10
  ---
12
11
 
13
12
  # Sassy Review
@@ -6,7 +6,6 @@ description: >-
6
6
  gist plus the brief path, never a wall of file contents. Use when a plan, fix,
7
7
  or review needs verified project evidence before it starts.
8
8
  argument-hint: "[the area or question to ground]"
9
- disable-model-invocation: true
10
9
  ---
11
10
 
12
11
  # Sassy Scout
@@ -8,7 +8,6 @@ description: >-
8
8
  Use when asked to set up or configure a project, or to check an existing
9
9
  setup (`mode:check`).
10
10
  argument-hint: "[path] [mode:init|check]"
11
- disable-model-invocation: true
12
11
  ---
13
12
 
14
13
  # Sassy Setup
@@ -6,7 +6,7 @@ The suite runs in any harness that loads Agent Skills — pi, Claude Code, and o
6
6
 
7
7
  "Load the `sassy-x` skill and follow it" means: read `sassy-x/SKILL.md` from the same skills directory as the skill you are running (its sibling, `../sassy-x/SKILL.md`), then follow it. "The `sassy-x` skill's `references/y.md`" is `../sassy-x/references/y.md`.
8
8
 
9
- Read the file; do not rely on the harness's skill-invocation tool. Suite skills set `disable-model-invocation: true`, and some harnesses (Claude Code) enforce that by hiding them from the model entirely. Reading the sibling file works everywhere.
9
+ Read the file; do not rely on the harness's skill-invocation tool. Not every harness exposes one, and those that do differ in how they resolve names. Reading the sibling file works everywhere.
10
10
 
11
11
  A missing sibling means the suite is incomplete: stop and point at `sassy-setup`.
12
12
 
@@ -7,7 +7,6 @@ description: >-
7
7
  applies all, mode:return only reports. Use when asked to simplify, tidy, or
8
8
  refactor recent changes. Leaves changes uncommitted.
9
9
  argument-hint: "[files, branch, or blank for current changes] [mode:manual|auto|return]"
10
- disable-model-invocation: true
11
10
  ---
12
11
 
13
12
  # Sassy Simplify
@@ -7,7 +7,6 @@ description: >-
7
7
  skill, turn a workflow into a skill, fix a description or triggering,
8
8
  restructure a bloated skill, or retune an existing one.
9
9
  argument-hint: "[mode:create|retune|verify] [name, idea, or skill path]"
10
- disable-model-invocation: true
11
10
  ---
12
11
 
13
12
  # Sassy Skill
@@ -7,7 +7,6 @@ description: >-
7
7
  mode:return only reports. Use when asked to verify conformance to a plan or
8
8
  intent. Leaves changes uncommitted.
9
9
  argument-hint: "[plan path + phase, or the intent to validate against] [mode:manual|auto|return]"
10
- disable-model-invocation: true
11
10
  ---
12
11
 
13
12
  # Sassy Validate
@@ -6,7 +6,6 @@ description: >-
6
6
  it was the last). Also runs one settled in-context brief and stops before ship.
7
7
  The orchestrator only coordinates.
8
8
  argument-hint: "<plan path | brief> [phase:<n>] [branch:infer|current|new]"
9
- disable-model-invocation: true
10
9
  ---
11
10
 
12
11
  # Sassy Work