PM Skill Iterate¶
Quick facts
Classification: Utility | Version: 1.0.0 | Category: coordination | License: Apache-2.0
This skill improves an existing pm-skills skill by applying targeted changes based on input you provide. It reads the current skill files, proposes changes as before/after previews grouped by file, and writes them on your confirmation. After applying changes, it suggests a version bump class and offers to update HISTORY.md.
The iterator accepts any of these as input:
- A validation report from /pm-skill-validate
- Direct feedback ("the template is missing section X")
- A convention change ("all skills now need a Limitations section")
- A general improvement request ("make the example more realistic")
When to Use¶
- After running
/pm-skill-validateand getting a report with findings - When you have specific feedback on a skill and want to apply it
- When a repo convention changes and a skill needs to conform
- When a skill's example, template, or instructions need improvement
- When iterating on a skill before a release
When NOT to Use¶
- To create a new skill from scratch -> use
/pm-skill-builder - To audit a skill before making changes -> use
/pm-skill-validatefirst - To make bulk convention changes across many skills -> run
/pm-skill-validate --allfirst to triage, then iterate one skill at a time
How to Use¶
Use the /pm-skill-iterate slash command:
Or reference the skill file directly: skills/utility-pm-skill-iterate/SKILL.md
Instructions¶
When asked to iterate on a skill, follow these steps:
Step 1: Identify the Target Skill¶
Accept the skill name in any form:
- Directory name: deliver-prd
- Full path: skills/deliver-prd/SKILL.md
- Slash command: /prd
Resolve to the canonical directory path: skills/{name}/.
If the skill directory does not exist, stop and report: "Skill directory
skills/{name}/ does not exist. Use /pm-skill-builder to create it."
Step 2: Read Current Skill Files¶
Read all files in the skill directory:
| File | Required | Purpose |
|---|---|---|
SKILL.md |
yes | Frontmatter + instructions (the primary edit target) |
references/TEMPLATE.md |
yes | Output template |
references/EXAMPLE.md |
yes | Worked example |
HISTORY.md |
no | Version history (needed for Step 7) |
Record the exact content of each file at this point. You will compare against this content before writing in Step 5 (stale-preview guard).
If reading files is not possible (MCP/embedded environment), ask the user to paste the relevant file contents before proceeding (see Degraded Mode).
Step 3: Normalize Input into Intended Changes¶
Regardless of input type, extract a structured list of intended changes before generating any edits. This normalization step is what makes the unified flow work consistently across all input types.
If the input is a validation report (from /pm-skill-validate):
- Check for Report schema: v1 in the header. If absent or a different
schema version, warn: "This report uses an unrecognized schema. I'll
do my best but may miss structured fields."
- Parse the ## Recommendations section.
- Split each recommendation line on | to extract:
- Position 1: severity (FAIL, WARN, INFO)
- Position 2: check ID
- After Target:: file path
- After Action: (next line): what to change
- Build the intended changes list from these fields.
If the input is free text (feedback, convention change, improvement request): - Read the input and identify what needs to change. - Map each change to a specific target file and section. - If the input is vague, ask ONE clarifying question before proceeding.
Present the normalized list for user confirmation:
Intended changes:
1. Target: skills/{name}/SKILL.md -> {section}
Change: {what will change}
Source: {validation report check ID | user feedback | convention change}
2. Target: skills/{name}/references/EXAMPLE.md -> {section}
Change: {what will change}
Source: {source}
If the user wants to modify the list (add, remove, or change items), adjust and re-present before proceeding.
Step 4: Preview Proposed Changes¶
For each intended change, generate the proposed edit and present it as a before/after block grouped by file:
### skills/{name}/SKILL.md
**{Section name} -- before:**
> {exact current content of the section being changed}
**{Section name} -- after:**
> {proposed new content for this section}
### skills/{name}/references/EXAMPLE.md
**{Section name} -- before:**
> {exact current content}
**{Section name} -- after:**
> {proposed new content}
Preview rules: - Group all changes by file. Show each file once, with all its changes. - Show enough surrounding context for the user to understand the change. - For small edits (a few lines), show the full section before and after. - For large edits (rewriting most of a section), show the section header and the first/last few lines of before, then the full after. - Do NOT show files that are not being changed.
Ask: "Apply these changes? [yes / no]"
If the user says no, ask what to adjust and return to Step 3 or Step 4.
Step 5: Apply Changes (with Stale-Preview Guard)¶
Before writing any file, re-read each target file and compare its content to what you recorded in Step 2.
If any target file has changed since Step 2:
- Do NOT write any files.
- Report: "File {path} has changed since the preview was generated.
Regenerating preview with current content."
- Return to Step 2 with the same intended changes list.
If all target files match:
- Write the changes to each target file.
- Update the updated field in SKILL.md frontmatter to today's date.
(The updated field tracks when the file was last modified, regardless
of whether a version bump is accepted.)
- Report what was written: list each file and a one-line summary of
what changed.
Step 6: Suggest Version Bump¶
After changes are applied, classify the overall change and suggest a version bump class. Do NOT auto-write the version number.
Classification rules (from docs/internal/skill-versioning.md):
| Change type | Bump class | Examples |
|---|---|---|
| Wording clarified, examples improved, typos fixed | patch | Reworded checklist item, better example scenario, description expanded |
| New optional capability or section added | minor | New optional output section, handles more scenarios, new quality check |
| Required contract changed, interaction pattern breaks | major | Command renamed, required section removed, "done" definition narrowed |
Tie-breaker: If a user must do something new to stay compliant with the skill's required contract, classify as major. If the new behavior is additive or optional, classify as minor. If the required behavior is unchanged and only clarified, classify as patch.
Present the suggestion:
Suggested bump: {class} ({reason}).
Current version: {current}.
Bump to {suggested}? [yes / override / skip]
- yes: Write the new version to SKILL.md frontmatter.
- override: Ask for the desired version, validate it's valid SemVer and higher than current, then write it.
- skip: Leave the version unchanged. The user may bump it later during release prep.
Step 7: Offer HISTORY.md Update¶
After the version decision, produce a change summary and handle HISTORY.md based on the current state:
If HISTORY.md exists and version was bumped:
1. Read HISTORY.md and validate its format:
- Has a summary table with | Version | Date | Release | ... header
- Versions are newest-first in the table
- Each table version has a corresponding ## X.Y.Z section below
2. If format is valid: offer to append.
"Would you like me to add this version to HISTORY.md? [yes / no]"
On yes: add a new row to the summary table (newest-first) and a new
## X.Y.Z section with the change summary.
3. If format is invalid: warn and show the proposed content without
writing. "HISTORY.md doesn't follow the expected format. Here's what
I would add -- you can paste it manually:"
Then show the proposed table row and version section.
If HISTORY.md does not exist and this is the skill's second version:
Offer to create it. "This is the second version of this skill. Would you
like me to create HISTORY.md with entries for both versions? [yes / no]"
On yes: create HISTORY.md with the format from docs/internal/skill-versioning.md,
including entries for both the original version (from release history or
effort brief) and the new version.
If HISTORY.md does not exist and version was not bumped: No offer. HISTORY.md is premature until the skill has shipped a second version.
If HISTORY.md exists but version was not bumped (skip): No offer. The change summary is available in the conversation for the user to use at their discretion.
Step 8: Report Summary¶
Present a final summary:
```
Output Template¶
Iteration Change Summary:¶
Intended Changes¶
{Normalized list of changes extracted from input.}
- Target: {file-path} -> {section} Change: {what will change} Source: {validation report check ID | user feedback | convention change}
Proposed Changes¶
{Before/after previews grouped by file.}
{file-path}¶
{Section name} -- before:
{current content}
{Section name} -- after:
{proposed content}
Applied Changes¶
{Summary of what was actually written after user confirmation.}
| File | Change |
|---|---|
| {file-path} | {one-line summary} |
Version¶
Current: {version} Suggested bump: {class} ({reason}) New version: {new-version | unchanged}
HISTORY.md¶
{One of: updated | created | skipped | not applicable}
{If updated or created, show the content that was written.}
Example Output¶
Iteration Example: deliver-prd
Iteration Example: deliver-prd¶
This example shows a validation-report-driven iteration of deliver-prd.
The input is the WARN finding from the F-10 validation report example
(output-contract-coverage).
Step 1: Identify the Target Skill¶
Target: skills/deliver-prd/
Resolved from user input: /pm-skill-iterate deliver-prd
Step 2: Read Current Skill Files¶
Read and recorded:
- skills/deliver-prd/SKILL.md (72 lines)
- skills/deliver-prd/references/TEMPLATE.md (10 sections)
- skills/deliver-prd/references/EXAMPLE.md (212 lines)
- HISTORY.md does not exist
Step 3: Normalize Input into Intended Changes¶
Input: validation report from /pm-skill-validate deliver-prd
Parsed ## Recommendations section (Report schema: v1):
Intended changes:
1. Target: skills/deliver-prd/SKILL.md -> Output Format section
Change: Enumerate template sections explicitly instead of generic reference
Source: validation report, check output-contract-coverage
The INFO finding (when-not-to-use) was excluded from the intended changes
list because the user did not request it. INFO findings are optional and
only included if the user explicitly asks for them.
"Proceed with this change? [yes / no]"
User: yes
Step 4: Preview Proposed Changes¶
skills/deliver-prd/SKILL.md¶
Output Format section -- before:
Output Format¶
Use the template in
references/TEMPLATE.mdto structure the output.
Output Format section -- after:
Output Format¶
Use the template in
references/TEMPLATE.mdto structure the output. The output MUST include these sections:
- Overview
- Goals & Success Metrics
- User Stories
- Scope
- Solution Design
- Technical Considerations
- Dependencies & Risks
- Timeline & Milestones
- Open Questions
- Appendix
No changes to references/TEMPLATE.md or references/EXAMPLE.md.
"Apply these changes? [yes / no]"
User: yes
Step 5: Apply Changes (with Stale-Preview Guard)¶
Re-read skills/deliver-prd/SKILL.md -- content matches Step 2 recording.
No stale-preview conflict.
Changes applied:
- skills/deliver-prd/SKILL.md -- expanded Output Format section with
explicit template section enumeration
- updated field changed from 2026-01-26 to 2026-04-03
Step 6: Suggest Version Bump¶
The change clarifies the output contract by making implicit requirements explicit. Users who previously followed the template were already producing compliant output -- nothing new is required. This is a patch change.
Suggested bump: patch (output contract clarification -- makes template
section requirements explicit without adding new requirements).
Current version: 2.0.0.
Bump to 2.0.1? [yes / override / skip]
User: yes
Version updated: 2.0.0 -> 2.0.1 in SKILL.md frontmatter.
Step 7: Offer HISTORY.md Update¶
HISTORY.md does not exist. This is the skill's second version (2.0.0 -> 2.0.1).
"This is the second version of this skill. Would you like me to create HISTORY.md with entries for both versions? [yes / no]"
User: yes
Created skills/deliver-prd/HISTORY.md:
```markdown
deliver-prd -- Version History¶
| Version | Date | Release | Effort | Type | Summary |
|---|---|---|---|---|---|
| 2.0.1 | 2026-04-03 | TBD | -- | changed | Output contract clarification |
| 2.0.0 | 2026-01-26 | v2.0.0 | -- | added | v2.0 restructure |
2.0.1 (2026-04-03)¶
Release: TBD.
Expanded the Output Format section to explicitly enumerate all 10 template sections instead of a generic "use the template" reference. No new requirements -- existing compliant output remains valid.
Changes¶
- Output Format section now lists all 10 TEMPLATE.md sections by name
- Clarifies which sections are required in the output
2.0.0 (2026-01-26)¶
Released in v2.0.0.
Restructured as part of the v2.0 flat-extensions migration. Established the current skill structure with frontmatter, instructions, output contract, and quality checklist.
Contract established¶
- Command: /prd
- Phase: deliver
- Output: Product Requirements Document following TEMPLATE.md structure ```
Step 8: Report Summary¶
```
Iteration Complete: deliver-prd¶
Files changed: - skills/deliver-prd/SKILL.md -- expanded Output Format with explicit section list - skills/deliver-prd/HISTORY.md -- created (first iteration, two-version history)
Version: 2.0.0 -> 2.0.1 (patch) HISTORY.md: created
Next steps:
- Run /pm-skill-validate deliver-prd to verify the changes pass
- Run local CI: bash scripts/lint-skills-frontmatter.sh
- If satisfied, commit the changes
```
Example Notes¶
This example demonstrates:
- Validation-report-driven iteration: the input is a structured report
from /pm-skill-validate, parsed by ## Recommendations and pipe-delimited fields
- INFO findings excluded by default: the when-not-to-use INFO was not
included in the intended changes because the user did not request it
- Before/after preview: the Output Format section shown in full before
and after, grouped under the target file heading
- Stale-preview guard: Step 5 explicitly re-reads the target file and
confirms it matches the Step 2 recording before writing
- Patch classification: making implicit requirements explicit is a
clarification, not a new requirement -- users who followed the template
were already producing compliant output
- HISTORY.md creation at second-version trigger: the skill moved from
2.0.0 to 2.0.1, triggering the governance rule to create HISTORY.md
with entries for both versions
- The iteration did NOT modify TEMPLATE.md or EXAMPLE.md: the change
was confined to SKILL.md's Output Format section
Quality Checklist¶
Before completing the iteration, verify:
- Input was normalized into an intended-changes list before editing
- All proposed changes were shown as before/after previews
- User confirmed before any files were written
- Stale-preview guard ran before writing (or noted as unavailable)
-
updateddate was set to today in SKILL.md frontmatter - Version bump class was suggested with correct reasoning
- Version was only written after explicit user confirmation
- HISTORY.md was handled correctly per Step 7 rules
- Final summary was presented with next steps
Output Contract¶
The iterator MUST:
- Normalize input into a structured intended-changes list before editing
- Present all proposed changes as before/after previews grouped by file
- Require explicit user confirmation before writing any file
- Re-read target files before writing to guard against stale previews
- Update the updated frontmatter field on every apply
- Suggest a version bump class without auto-writing the version number
- Handle HISTORY.md according to the rules in Step 7
The iterator MUST NOT: - Write files without showing a preview first - Write files without user confirmation - Auto-increment the version number without explicit confirmation - Create HISTORY.md for a skill still on its first version - Append to HISTORY.md without validating its format first