session-management
Context preservation, tiered summarization, resumability
40
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/session-management/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically weak across all dimensions. It reads as a comma-separated list of abstract concepts rather than a functional skill description, providing no concrete actions, no trigger guidance, and no clarity on when it should be selected. It would be nearly impossible for Claude to reliably choose this skill from a pool of available options.
Suggestions
Rewrite using active verbs describing concrete actions, e.g., 'Summarizes long conversations into tiered summaries, preserves key context across sessions, and enables resumption of interrupted tasks.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to resume a previous conversation, needs a summary of prior context, or asks to pick up where they left off.'
Include natural user-facing keywords like 'resume', 'continue conversation', 'summarize chat', 'remember context', 'catch up' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract nouns ('context preservation', 'tiered summarization', 'resumability') without describing any concrete actions. There are no verbs indicating what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and the 'what' is only vaguely implied through abstract noun phrases. | 1 / 3 |
Trigger Term Quality | The terms used are technical jargon ('context preservation', 'resumability', 'tiered summarization') that users would almost never naturally say when requesting help. Users would more likely say things like 'summarize conversation', 'pick up where we left off', or 'remember context'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely vague and could overlap with many skills involving summarization, memory, or conversation management. Without specific triggers or a clear niche, it would be very difficult to distinguish from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent concrete templates and a well-designed tiered checkpoint system, but it is severely undermined by extreme verbosity and lack of progressive disclosure. The same decision logic is repeated 3-4 times across different sections, and lengthy file templates that should be separate reference files are all inlined, making this a ~350-line monolith that wastes significant context window space.
Suggestions
Extract the file templates (current-state.md, decisions.md, code-landmarks.md, archive template) into separate reference files and link to them from the main skill with one-line descriptions.
Eliminate the repeated checkpoint decision logic - it appears in Tiered Summarization Rules, CLAUDE.md Session Rules, Enforcement Self-Check Questions, and Quick Reference. Keep it in one canonical location.
Move the CLAUDE.md integration section, bash aliases, and enforcement mechanisms into a separate setup/configuration reference file.
Aim to reduce the main SKILL.md to under 100 lines: core principle, tiered trigger table, directory structure, and links to detailed templates/references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~350+ lines. It includes extensive template examples with placeholder content (JWT auth examples, Drizzle ORM decisions) that are illustrative but massively inflate token count. The same checkpoint decision logic is repeated at least 3 times (tiered rules, CLAUDE.md rules, enforcement self-check, quick reference). Much of this could be compressed to under 100 lines. | 1 / 3 |
Actionability | The skill provides fully concrete, copy-paste ready templates for every file (current-state.md, decisions.md, code-landmarks.md, archive templates), specific directory structures, bash aliases, and detailed examples with realistic content. Every instruction is specific and executable. | 3 / 3 |
Workflow Clarity | The tiered summarization system provides clear triggers, actions, and decision heuristics with an explicit decision tree. Session start and end protocols are well-sequenced with numbered steps. The periodic self-audit mechanism serves as a validation checkpoint for context management. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inline. The extensive file templates (current-state.md, decisions.md, code-landmarks.md, archive template) should be separate reference files. The CLAUDE.md section, bash aliases, and enforcement mechanisms all bloat the main skill file when they could be referenced externally. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (530 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
d4ddb03
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.