claude-dev-env 1.19.2 → 1.19.3
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/package.json
CHANGED
|
@@ -62,8 +62,8 @@ The feedback loop: observe Claude B's behavior, bring insights back, refine the
|
|
|
62
62
|
|
|
63
63
|
When building a **new** skill as a **full package** (architecture inventory, progressive disclosure files, `evals/`, **human checkpoint after each file**), treat the following as **mandatory** before implementation:
|
|
64
64
|
|
|
65
|
-
- **Read:** `prompt-generator/templates/skill-from-ground-up.md`
|
|
66
|
-
- **Do:** Run `/prompt-generator`
|
|
65
|
+
- **Read:** the installed `@jl-cmd/prompt-generator` template `prompt-generator/templates/skill-from-ground-up.md` (upstream repository path: `skills/prompt-generator/templates/skill-from-ground-up.md` in [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
66
|
+
- **Do:** Run `/prompt-generator` using that installed template with the file’s token table filled so the downstream session follows architecture-first sequencing, per-file review gates, and eval rows tied only to user-pasted or explicitly approved evidence.
|
|
67
67
|
|
|
68
68
|
Use this **together with** gap-analysis and eval-scenario templates in this package; the ground-up template supplies the **orchestration contract** for the multi-file layout Anthropic recommends.
|
|
69
69
|
|
|
@@ -71,7 +71,7 @@ Use this **together with** gap-analysis and eval-scenario templates in this pack
|
|
|
71
71
|
|
|
72
72
|
When **improving** an existing skill as a **multi-file** or **checkpointed** package (baseline directory plus planned deltas, observation-grounded evals), treat the following as **mandatory** before Phase 2–6 file work in `improve-skill.md` or package-aware steps in `polish-skill.md`:
|
|
73
73
|
|
|
74
|
-
- **Read:** `prompt-generator/templates/skill-refinement-package.md` (repository path: `
|
|
74
|
+
- **Read:** `prompt-generator/templates/skill-refinement-package.md` (repository path: `skills/prompt-generator/templates/skill-refinement-package.md` in [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
75
75
|
- **Do:** Run `/prompt-generator` with that file’s token table filled (`[[BASELINE_SKILL_ROOT]]`, `[[WORKSPACE_ROOT]]`, observation gap path, evidence rule) so rollout stays architecture-first, delta-focused, and tied to real observation or approved excerpts.
|
|
76
76
|
|
|
77
77
|
Net-new packages without a baseline skill directory use `skill-from-ground-up.md` instead.
|
|
@@ -55,7 +55,7 @@ From here, follow the same phases as `${CLAUDE_SKILL_DIR}/workflows/new-skill.md
|
|
|
55
55
|
|
|
56
56
|
Whenever Phases 2–6 will touch **multiple files**, **progressive disclosure layout**, or use **checkpointed file-by-file rollout**, treat this as **required** before expanding or rewriting the tree:
|
|
57
57
|
|
|
58
|
-
1. Read `
|
|
58
|
+
1. Read `skill-refinement-package.md` from the installed prompt-generator skill, typically at `~/.claude/skills/prompt-generator/templates/skill-refinement-package.md` (source dependency: [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
59
59
|
2. Run `/prompt-generator` with that template’s token table filled: set `[[BASELINE_SKILL_ROOT]]` to the existing skill directory, `[[WORKSPACE_ROOT]]` to your iteration workspace (in-place or snapshot per user preference), and `[[DESIGN_INPUT_GLOB]]` to this workflow’s observation-based `gap-analysis.md` when it exists.
|
|
60
60
|
|
|
61
61
|
Use `skill-from-ground-up.md` **only** for **greenfield** packages where no baseline skill directory exists yet; use `skill-refinement-package.md` for every refinement anchored to an existing skill.
|
|
@@ -11,7 +11,7 @@ Full evaluation-driven lifecycle for building a new skill from scratch.
|
|
|
11
11
|
|
|
12
12
|
When the outcome includes **ARCHITECTURE.md**, **REFERENCE / EXAMPLES / WORKFLOWS**, and **`evals/*.json`** under a workspace (Anthropic-style progressive disclosure plus checkpointed rollout):
|
|
13
13
|
|
|
14
|
-
1. Read `prompt-generator/templates/skill-from-ground-up.md` from the claude
|
|
14
|
+
1. Read `prompt-generator/templates/skill-from-ground-up.md` from the installed `~/.claude/skills/` tree (provided by [@jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
15
15
|
2. Run `/prompt-generator` using that template (substitute tokens per its table) **before** Phase 3 expands the repo; align the XML scope block with this workflow’s workspace and evidence rules.
|
|
16
16
|
3. Keep Phase 1–2 artifacts honest: eval prompts and expectations stay grounded in **real** user scenarios; the template reinforces eval rows that reference pasted or explicitly approved evidence only.
|
|
17
17
|
|
|
@@ -12,7 +12,7 @@ Final optimization pass for a skill that is functionally complete.
|
|
|
12
12
|
|
|
13
13
|
When the polish pass will touch **more than frontmatter alone** (for example `REFERENCE.md`, `EXAMPLES.md`, `WORKFLOWS.md`, link structure, or eval JSON), or the user wants **checkpointed** multi-file updates alongside description work:
|
|
14
14
|
|
|
15
|
-
1. Read `prompt-generator/templates/skill-refinement-package.md` (repository path: `
|
|
15
|
+
1. Read `prompt-generator/templates/skill-refinement-package.md` (repository path: `skills/prompt-generator/templates/skill-refinement-package.md` in [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
16
16
|
2. Run `/prompt-generator` with tokens filled so `ARCHITECTURE.md` records baseline inventory, planned deltas for polish, and evidence rules for any new trigger or behavior evals.
|
|
17
17
|
|
|
18
18
|
Purely **single-field** `description` edits with no structural package changes can skip this block.
|
|
@@ -36,7 +36,7 @@ When invoked with arguments (e.g. `/skill-writer improve this: [paste]`), treat
|
|
|
36
36
|
|
|
37
37
|
When the user is creating a **new** skill as a **package** (workspace with `ARCHITECTURE.md`, `REFERENCE.md`, `EXAMPLES.md`, `WORKFLOWS.md`, `evals/*.json`, per-file human review), **before** drafting `SKILL.md`:
|
|
38
38
|
|
|
39
|
-
1. Read `
|
|
39
|
+
1. Read `prompt-generator/templates/skill-from-ground-up.md` (installed layout: sibling folder under the same `skills/` parent; repository path: `skills/prompt-generator/templates/skill-from-ground-up.md` in [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
40
40
|
2. Ensure `/prompt-generator` has run with that template filled so architecture-first steps, checkpoint gates, and eval evidence rules are already agreed.
|
|
41
41
|
|
|
42
42
|
If the task is **only** editing an existing `SKILL.md` or a small single-file tweak, this subsection does not apply.
|
|
@@ -45,7 +45,7 @@ If the task is **only** editing an existing `SKILL.md` or a small single-file tw
|
|
|
45
45
|
|
|
46
46
|
When the user is **refining** an existing skill as a **package** (baseline skill directory, `ARCHITECTURE.md` with planned deltas, checkpointed updates to REFERENCE / EXAMPLES / WORKFLOWS / `evals/`), **before** rewriting multiple files:
|
|
47
47
|
|
|
48
|
-
1. Read `
|
|
48
|
+
1. Read `prompt-generator/templates/skill-refinement-package.md` (installed layout: under the same `skills/` parent; repository path: `skills/prompt-generator/templates/skill-refinement-package.md` in [jl-cmd/prompt-generator](https://github.com/jl-cmd/prompt-generator)).
|
|
49
49
|
2. Ensure `/prompt-generator` has run with that template filled so baseline root, workspace root, observation inputs, and evidence rules are fixed before edits proceed.
|
|
50
50
|
|
|
51
51
|
If the change set is a **small single-file** tweak, this subsection does not apply.
|